Jianping Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jianping Wu has a total of 122 co-authors. Here are the top co-authors by number of shared publications:
- Ke Xu
Tsinghua University, Beijing, China
7 shared publications - Ke Xu
Department of Computer Science and Technology, Tsinghua University, Beijing, China
5 shared publications Qian Wu
IEEE Tsinghua University Beijing China
4 shared publicationsKe Xu
3 shared publicationsQi Li
Tsinghua University
3 shared publications- Qi Li
Tsinghua University, Beijing, China
3 shared publications
Latest Publications
- 1 October 2026
- Published by RFC Editor
Problem Statement, Gap Analysis, and Requirements for Intra-Domain Source Address Validation
Source Address Validation (SAV) is an important means to mitigate IP source address spoofing (RFC 2827). This document analyzes the gaps in current operational mechanisms for intra-domain SAV. It also identifies the properties that new intra-domain SAV mechanisms are expected to provide.
- 1 October 2026
- Published by RFC Editor
Problem Statement, Gap Analysis, and Requirements for Intra-Domain Source Address Validation
Source Address Validation (SAV) is an important means to mitigate IP source address spoofing (RFC 2827). This document analyzes the gaps in current operational mechanisms for intra-domain SAV. It also identifies the properties that new intra-domain SAV mechanisms are expected to provide.
- Open Access
Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted traffic exchanged between users and LLM agents. By analyzing traffic patterns associated with agent workflows and tool invocations, adversaries can infer agent activities, distinguish specific agents, and even profile sensitive user attributes. To highlight this risk, we develop AgentPrint, which achieves an F1-score of 0.866 in agent identification and attains 73.9% and 69.1% top-3 accuracy in user attribute inference for simulated- and real-user settings, respectively. These results uncover an overlooked risk: the very interactivity that empowers LLM agents also exposes user privacy, underscoring the urgent need for technical countermeasures alongside regulatory and policy safeguards.
Open AccessExposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted traffic exchanged between users and LLM agents. By analyzing traffic patterns associated with agent workflows and tool invocations, adversaries can infer agent activities, distinguish specific agents, and even profile sensitive user attributes. To highlight this risk, we develop AgentPrint, which achieves an F1-score of 0.866 in agent identification and attains 73.9% and 69.1% top-3 accuracy in user attribute inference for simulated- and real-user settings, respectively. These results uncover an overlooked risk: the very interactivity that empowers LLM agents also exposes user privacy, underscoring the urgent need for technical countermeasures alongside regulatory and policy safeguards.
- Open Access
Towards Robust Multi-tab Website Fingerprinting
Website fingerprinting enables an eavesdropper to determine which websites a user is visiting over an encrypted connection. State-of-the-art website fingerprinting (WF) attacks have demonstrated effectiveness even against Tor-protected network traffic. However, existing WF attacks have critical limitations on accurately identifying websites in multi-tab browsing sessions, where the holistic pattern of individual websites is no longer preserved, and the number of tabs opened by a client is unknown a priori. In this paper, we propose ARES, a novel WF framework natively designed for multi-tab WF attacks. ARES formulates the multi-tab attack as a multi-label classification problem and solves it using the novel Transformer-based models. Specifically, ARES extracts local patterns based on multi-level traffic aggregation features and utilizes the improved self-attention mechanism to analyze the correlations between these local patterns, effectively identifying websites. We implement a prototype of ARES and extensively evaluate its effectiveness using our large-scale datasets collected over multiple months. The experimental results illustrate that ARES achieves optimal performance in several realistic scenarios. Further, ARES remains robust even against various WF defenses.
Open AccessTowards Robust Multi-tab Website Fingerprinting
Website fingerprinting enables an eavesdropper to determine which websites a user is visiting over an encrypted connection. State-of-the-art website fingerprinting (WF) attacks have demonstrated effectiveness even against Tor-protected network traffic. However, existing WF attacks have critical limitations on accurately identifying websites in multi-tab browsing sessions, where the holistic pattern of individual websites is no longer preserved, and the number of tabs opened by a client is unknown a priori. In this paper, we propose ARES, a novel WF framework natively designed for multi-tab WF attacks. ARES formulates the multi-tab attack as a multi-label classification problem and solves it using the novel Transformer-based models. Specifically, ARES extracts local patterns based on multi-level traffic aggregation features and utilizes the improved self-attention mechanism to analyze the correlations between these local patterns, effectively identifying websites. We implement a prototype of ARES and extensively evaluate its effectiveness using our large-scale datasets collected over multiple months. The experimental results illustrate that ARES achieves optimal performance in several realistic scenarios. Further, ARES remains robust even against various WF defenses.
- Open Access
Exploiting Cross-Layer Vulnerabilities: Off-Path Attacks on the TCP/IP Protocol Suite
After more than 40 years of development, the fundamental TCP/IP protocol suite, serving as the backbone of the Internet, is widely recognized for having achieved an elevated level of robustness and security. Distinctively, we take a new perspective to investigate the security implications of cross-layer interactions within the TCP/IP protocol suite caused by ICMP error messages. Through a comprehensive analysis of interactions among Wi-Fi, IP, ICMP, UDP, and TCP due to ICMP errors, we uncover several significant vulnerabilities, including information leakage, desynchronization, semantic gaps, and identity spoofing. These vulnerabilities can be exploited by off-path attackers to manipulate network traffic stealthily, affecting over 20% of popular websites and more than 89% of public Wi-Fi networks, thus posing risks to the Internet. By responsibly disclosing these vulnerabilities to affected vendors and proposing effective countermeasures, we enhance the robustness of the TCP/IP protocol suite, receiving acknowledgments from well-known organizations such as the Linux community, the OpenWrt community, the FreeBSD community, Wi-Fi Alliance, Qualcomm, HUAWEI, China Telecom, Alibaba, and H3C.
Open AccessExploiting Cross-Layer Vulnerabilities: Off-Path Attacks on the TCP/IP Protocol Suite
After more than 40 years of development, the fundamental TCP/IP protocol suite, serving as the backbone of the Internet, is widely recognized for having achieved an elevated level of robustness and security. Distinctively, we take a new perspective to investigate the security implications of cross-layer interactions within the TCP/IP protocol suite caused by ICMP error messages. Through a comprehensive analysis of interactions among Wi-Fi, IP, ICMP, UDP, and TCP due to ICMP errors, we uncover several significant vulnerabilities, including information leakage, desynchronization, semantic gaps, and identity spoofing. These vulnerabilities can be exploited by off-path attackers to manipulate network traffic stealthily, affecting over 20% of popular websites and more than 89% of public Wi-Fi networks, thus posing risks to the Internet. By responsibly disclosing these vulnerabilities to affected vendors and proposing effective countermeasures, we enhance the robustness of the TCP/IP protocol suite, receiving acknowledgments from well-known organizations such as the Linux community, the OpenWrt community, the FreeBSD community, Wi-Fi Alliance, Qualcomm, HUAWEI, China Telecom, Alibaba, and H3C.
- Open Access
- 28 September 2024
- Published by MDPI AG in Electronics
- Vol. 13  (19) , 3855
Optimizing the Effectiveness of Moving Target Defense in a Probabilistic Attack Graph: A Deep Reinforcement Learning Approach
Moving target defense (MTD) technology baffles potential attacks by dynamically changing the software in use and/or its configuration while maintaining the application’s running states. But it incurs a deployment cost and various performance overheads, degrading performance. An attack graph is capable of evaluating the balance between the effectiveness and cost of an MTD deployment. In this study, we consider a network scenario in which each node in the attack graph can deploy MTD technology. We aim to achieve MTD deployment effectiveness optimization (MTD-DO) in terms of minimizing the network security loss under a limited budget. The existing related works either considered only a single node for deploying an MTD or they ignored the deployment cost. We first establish a non-linear MTD-DO formulation. Then, two deep reinforcement learning-based algorithms are developed, namely, deep Q-learning (DQN) and proximal policy optimization (PPO). Moreover, two metrics are defined in order to effectively evaluate MTD-DO algorithms with varying network scales and budgets. The experimental results indicate that both PPO- and DQN-based algorithms perform better than Q-learning-based and random algorithms. The DQN-based algorithm converges more quickly and performs, in terms of reward, marginally better than the PPO-based algorithm.
- 28 September 2024
- Published by MDPI AG in Electronics
- Vol. 13  (19) , 3855
Open AccessOptimizing the Effectiveness of Moving Target Defense in a Probabilistic Attack Graph: A Deep Reinforcement Learning Approach
Moving target defense (MTD) technology baffles potential attacks by dynamically changing the software in use and/or its configuration while maintaining the application’s running states. But it incurs a deployment cost and various performance overheads, degrading performance. An attack graph is capable of evaluating the balance between the effectiveness and cost of an MTD deployment. In this study, we consider a network scenario in which each node in the attack graph can deploy MTD technology. We aim to achieve MTD deployment effectiveness optimization (MTD-DO) in terms of minimizing the network security loss under a limited budget. The existing related works either considered only a single node for deploying an MTD or they ignored the deployment cost. We first establish a non-linear MTD-DO formulation. Then, two deep reinforcement learning-based algorithms are developed, namely, deep Q-learning (DQN) and proximal policy optimization (PPO). Moreover, two metrics are defined in order to effectively evaluate MTD-DO algorithms with varying network scales and budgets. The experimental results indicate that both PPO- and DQN-based algorithms perform better than Q-learning-based and random algorithms. The DQN-based algorithm converges more quickly and performs, in terms of reward, marginally better than the PPO-based algorithm.
- 3 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32  (5) , 4040-4055
Fast Software IPv6 Lookup With Neurotrie
IPv6 has shown notable growth in recent years, imposing the need for high-speed IPv6 lookup. As the forwarding rate of virtual switches continues increasing, software-based IPv6 lookup without using special hardware such as TCAM, GPU, and FPGA is of academic interest and industrial importance. Existing studies achieve fast software IPv4 lookup by reducing the operation number, as well as reducing the memory footprint to benefit from CPU cache. However, in the situation of 128-bit IPv6 addresses, it is challenging to keep both operation numbers and memory footprints small. To address the issue, we propose the Neurotrie data structure, which supports fast lookup and arbitrary strides. Thus, a good balance can be made between trie depth and memory footprint by computing the proper stride for each Neurotrie node. We model the optimal Neurotrie problem which minimizes the depth with limited memory footprint and develop a pseudo-polynomial time baseline algorithm to construct Neurotrie using dynamic programming. To improve the performance and reduce the computation complexity, we develop a deep reinforcement learning-based approach, which leverages a deep neural network to construct Neurotrie efficiently, based on characteristics captured from real IPv6 prefixes. We further refine the data structure called Neurotrie-S and develop an efficient mechanism for routing updates. Experiments on real routing tables show that Neurotrie-S achieves a lookup rate 34% higher than that of state-of-the-art approaches. We implement a Neurotrie-based software switch, and the forwarding rate of Neurotrie-S is about 10% to 345% higher than other algorithms.
- 3 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32  (5) , 4040-4055
Fast Software IPv6 Lookup With Neurotrie
IPv6 has shown notable growth in recent years, imposing the need for high-speed IPv6 lookup. As the forwarding rate of virtual switches continues increasing, software-based IPv6 lookup without using special hardware such as TCAM, GPU, and FPGA is of academic interest and industrial importance. Existing studies achieve fast software IPv4 lookup by reducing the operation number, as well as reducing the memory footprint to benefit from CPU cache. However, in the situation of 128-bit IPv6 addresses, it is challenging to keep both operation numbers and memory footprints small. To address the issue, we propose the Neurotrie data structure, which supports fast lookup and arbitrary strides. Thus, a good balance can be made between trie depth and memory footprint by computing the proper stride for each Neurotrie node. We model the optimal Neurotrie problem which minimizes the depth with limited memory footprint and develop a pseudo-polynomial time baseline algorithm to construct Neurotrie using dynamic programming. To improve the performance and reduce the computation complexity, we develop a deep reinforcement learning-based approach, which leverages a deep neural network to construct Neurotrie efficiently, based on characteristics captured from real IPv6 prefixes. We further refine the data structure called Neurotrie-S and develop an efficient mechanism for routing updates. Experiments on real routing tables show that Neurotrie-S achieves a lookup rate 34% higher than that of state-of-the-art approaches. We implement a Neurotrie-based software switch, and the forwarding rate of Neurotrie-S is about 10% to 345% higher than other algorithms.
- 19 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32  (4) , 3126-3141
Toward Practical Inter-Domain Source Address Validation
The Internet Protocol (IP) is the most fundamental building block of the Internet. However, it provides no explicit notion of packet-level authenticity. Such a weakness allows malicious actors to spoof IP packet headers and launch a wide variety of attacks. Meanwhile, the highly decentralized management of Internet infrastructure makes large-scale source address validation challenging in terms of overhead, validity, and flexibility. This paper presents a practical anti-spoofing approach, Source Address Validation Architecture eXternal (SAVA-X). SAVA-X introduces the concept of Address Domain to enable address validation in finer, prefix-level granularity. The address domains are organized in nested hierarchies to provide higher scalability and lower maintenance costs for partial deployment. We implement SAVA-X on commercial backbone routers and the P4 platform. The experiments indicate that the hardware implementation of SAVA-X can achieve 98% throughput on 100 Gbps links and close to the native IP forwarding in per-packet overhead, with less than 10 microseconds additional processing latency.
- 19 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Networking
- Vol. 32  (4) , 3126-3141
Toward Practical Inter-Domain Source Address Validation
The Internet Protocol (IP) is the most fundamental building block of the Internet. However, it provides no explicit notion of packet-level authenticity. Such a weakness allows malicious actors to spoof IP packet headers and launch a wide variety of attacks. Meanwhile, the highly decentralized management of Internet infrastructure makes large-scale source address validation challenging in terms of overhead, validity, and flexibility. This paper presents a practical anti-spoofing approach, Source Address Validation Architecture eXternal (SAVA-X). SAVA-X introduces the concept of Address Domain to enable address validation in finer, prefix-level granularity. The address domains are organized in nested hierarchies to provide higher scalability and lower maintenance costs for partial deployment. We implement SAVA-X on commercial backbone routers and the P4 platform. The experiments indicate that the hardware implementation of SAVA-X can achieve 98% throughput on 100 Gbps links and close to the native IP forwarding in per-packet overhead, with less than 10 microseconds additional processing latency.
- Open Access
Secure Inter-domain Routing and Forwarding via Verifiable Forwarding Commitments
The Internet inter-domain routing system is vulnerable. On the control plane, the de facto Border Gateway Protocol (BGP) does not have built-in mechanisms to authenticate routing announcements, so an adversary can announce virtually arbitrary paths to hijack network traffic; on the data plane, it is difficult to ensure that actual forwarding path complies with the control plane decisions. The community has proposed significant research to secure the routing system. Yet, existing secure BGP protocols (e.g., BGPsec) are not incrementally deployable, and existing path authorization protocols are not compatible with the current Internet routing infrastructure. In this paper, we propose FC-BGP, the first secure Internet inter-domain routing system that can simultaneously authenticate BGP announcements and validate data plane forwarding in an efficient and incrementally-deployable manner. FC-BGP is built upon a novel primitive, name Forwarding Commitment, to certify an AS's routing intent on its directly connected hops. We analyze the security benefits of FC-BGP in the Internet at different deployment rates. Further, we implement a prototype of FC-BGP and extensively evaluate it over a large-scale overlay network with 100 virtual machines deployed globally. The results demonstrate that FC-BGP saves roughly 55% of the overhead required to validate BGP announcements compared with BGPsec, and meanwhile FC-BGP introduces a small overhead for building a globally-consistent view on the desirable forwarding paths.
Open AccessSecure Inter-domain Routing and Forwarding via Verifiable Forwarding Commitments
The Internet inter-domain routing system is vulnerable. On the control plane, the de facto Border Gateway Protocol (BGP) does not have built-in mechanisms to authenticate routing announcements, so an adversary can announce virtually arbitrary paths to hijack network traffic; on the data plane, it is difficult to ensure that actual forwarding path complies with the control plane decisions. The community has proposed significant research to secure the routing system. Yet, existing secure BGP protocols (e.g., BGPsec) are not incrementally deployable, and existing path authorization protocols are not compatible with the current Internet routing infrastructure. In this paper, we propose FC-BGP, the first secure Internet inter-domain routing system that can simultaneously authenticate BGP announcements and validate data plane forwarding in an efficient and incrementally-deployable manner. FC-BGP is built upon a novel primitive, name Forwarding Commitment, to certify an AS's routing intent on its directly connected hops. We analyze the security benefits of FC-BGP in the Internet at different deployment rates. Further, we implement a prototype of FC-BGP and extensively evaluate it over a large-scale overlay network with 100 virtual machines deployed globally. The results demonstrate that FC-BGP saves roughly 55% of the overhead required to validate BGP announcements compared with BGPsec, and meanwhile FC-BGP introduces a small overhead for building a globally-consistent view on the desirable forwarding paths.
- 31 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34  (4) , 2041-2055
DARTScore: DuAl-Reconstruction Transformer for Video Captioning Evaluation
Video captioning evaluation aims at assessing the semantic consistency between video and candidate text, which should include measurement from two aspects: faithfulness (whether the information conveyed by candidate is correct w.r.t. video) and comprehensiveness (whether the main video content is covered by candidate). However, previous approaches have difficulty in evaluating faithfulness and comprehensiveness due to heavy reliance on references or heterogeneous of visual and textual data. In this paper, we propose a vision-involved evaluation metric based on a novel DuAl-Reconstruction Transformer, named DARTScore. DARTScore formulates the caption evaluation task as a dual-reconstruction problem to evaluate both faithfulness and comprehensiveness explicitly. Since the word in a candidate is usually related to several frames, DARTScore adaptively collects relevant frames to reconstruct the word and computes the reconstruction accuracy as faithfulness to inherently reflect whether the word information is contained in the video. In the inversive way, DARTScore reconstructs each frame with relevant words to evaluate comprehensiveness. By integrating fine-grained bidirectional reconstruction accuracies, DARTScore drills into each word in candidate and each frame in video to fully evaluate the semantic consistency. Furthermore, we collect and annotate two Chinese datasets with a large domain gap, named CRAETE-EVAL and VATEX-ZH-EVAL, to systematically evaluate existing metrics and fill the blank of Chinese video captioning evaluation. Experimental results show that DARTScore achieves higher correlation with human judgments, has lower reference reliance, and generalizes well to data from different domains.
- 31 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34  (4) , 2041-2055
DARTScore: DuAl-Reconstruction Transformer for Video Captioning Evaluation
Video captioning evaluation aims at assessing the semantic consistency between video and candidate text, which should include measurement from two aspects: faithfulness (whether the information conveyed by candidate is correct w.r.t. video) and comprehensiveness (whether the main video content is covered by candidate). However, previous approaches have difficulty in evaluating faithfulness and comprehensiveness due to heavy reliance on references or heterogeneous of visual and textual data. In this paper, we propose a vision-involved evaluation metric based on a novel DuAl-Reconstruction Transformer, named DARTScore. DARTScore formulates the caption evaluation task as a dual-reconstruction problem to evaluate both faithfulness and comprehensiveness explicitly. Since the word in a candidate is usually related to several frames, DARTScore adaptively collects relevant frames to reconstruct the word and computes the reconstruction accuracy as faithfulness to inherently reflect whether the word information is contained in the video. In the inversive way, DARTScore reconstructs each frame with relevant words to evaluate comprehensiveness. By integrating fine-grained bidirectional reconstruction accuracies, DARTScore drills into each word in candidate and each frame in video to fully evaluate the semantic consistency. Furthermore, we collect and annotate two Chinese datasets with a large domain gap, named CRAETE-EVAL and VATEX-ZH-EVAL, to systematically evaluate existing metrics and fill the blank of Chinese video captioning evaluation. Experimental results show that DARTScore achieves higher correlation with human judgments, has lower reference reliance, and generalizes well to data from different domains.
- 10 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet Computing
- Vol. 27  (3) , 44-49
SAV-D: Defending DDoS with Incremental Deployment of SAV
Large-scale Internet Protocol (IP) spoofing distributed denial-of-service (DDoS) attacks is one of the major cyber threats. Current commercial defenses focus on eliminating attacks at the destination end, which raises concerns about the cost of appliances and the impact on quality of service. As complementaries, source-end schemes using source address validation (SAV) can block IP spoofing traffic from entering the backbone. However, their effectiveness is restricted by incremental deployment. This paper proposes SAV-D, an SAV-based honeynet-like distributed defense architecture against IP spoofing DDoS. Each SAV device functions as a honeypot to capture more threat data. By aggregating these data, SAV-D can accurately detect ongoing attacks and generate defense policies. With the policies, both SAV and non-SAV devices can filter malicious traffic. Our simulation results demonstrate that SAV-D can effectively filter out 80% of attack traffic with a modest deployment ratio of only 10%. To enable broader adoption, we also provide some guidance on standardizing SAV-D.
- 10 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet Computing
- Vol. 27  (3) , 44-49
SAV-D: Defending DDoS with Incremental Deployment of SAV
Large-scale Internet Protocol (IP) spoofing distributed denial-of-service (DDoS) attacks is one of the major cyber threats. Current commercial defenses focus on eliminating attacks at the destination end, which raises concerns about the cost of appliances and the impact on quality of service. As complementaries, source-end schemes using source address validation (SAV) can block IP spoofing traffic from entering the backbone. However, their effectiveness is restricted by incremental deployment. This paper proposes SAV-D, an SAV-based honeynet-like distributed defense architecture against IP spoofing DDoS. Each SAV device functions as a honeypot to capture more threat data. By aggregating these data, SAV-D can accurately detect ongoing attacks and generate defense policies. With the policies, both SAV and non-SAV devices can filter malicious traffic. Our simulation results demonstrate that SAV-D can effectively filter out 80% of attack traffic with a modest deployment ratio of only 10%. To enable broader adoption, we also provide some guidance on standardizing SAV-D.