Yannick Teglia
Research Subjects
Yannick Teglia has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Valentin Martinoli
Cybersecurity Hardware lab Thales DIS La Ciotat France
2 shared publications - Abdellah Bouagoun
Cybersecurity Hardware lab Thales DIS La Ciotat France
1 shared publication - Cody Clop
Cybersecurity Artificial Intelligence Team Thales DIS 13600 La Ciotat France
1 shared publication - Elouan Tourneur
Thales DIS, 13600 La Ciotat, France
1 shared publication - Philippe Loubet-Moundi
Thales Cyber & Digital La Ciotat France
1 shared publication - Quentin Le Roux
Thales Cyber & Digital Inria/Univ. de Rennes La Ciotat & Rennes France
1 shared publication
Latest Publications
- Open Access
Backdoor Attacks on Deep Learning Face Detection
Face Recognition Systems that operate in unconstrained environments capture images under varying conditions,such as inconsistent lighting, or diverse face poses. These challenges require including a Face Detection module that regresses bounding boxes and landmark coordinates for proper Face Alignment. This paper shows the effectiveness of Object Generation Attacks on Face Detection, dubbed Face Generation Attacks, and demonstrates for the first time a Landmark Shift Attack that backdoors the coordinate regression task performed by face detectors. We then offer mitigations against these vulnerabilities.
Open AccessBackdoor Attacks on Deep Learning Face Detection
Face Recognition Systems that operate in unconstrained environments capture images under varying conditions,such as inconsistent lighting, or diverse face poses. These challenges require including a Face Detection module that regresses bounding boxes and landmark coordinates for proper Face Alignment. This paper shows the effectiveness of Object Generation Attacks on Face Detection, dubbed Face Generation Attacks, and demonstrates for the first time a Landmark Shift Attack that backdoors the coordinate regression task performed by face detectors. We then offer mitigations against these vulnerabilities.
- Open Access
Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities in generating coherent text but remain limited by the static nature of their training data. Retrieval Augmented Generation (RAG) addresses this issue by combining LLMs with up-to-date information retrieval, but also expand the attack surface of the system. This paper investigates prompt injection attacks on RAG, focusing on malicious objectives beyond misinformation, such as inserting harmful links, promoting unauthorized services, and initiating denial-of-service behaviors. We build upon existing corpus poisoning techniques and propose a novel backdoor attack aimed at the fine-tuning process of the dense retriever component. Our experiments reveal that corpus poisoning can achieve significant attack success rates through the injection of a small number of compromised documents into the retriever corpus. In contrast, backdoor attacks demonstrate even higher success rates but necessitate a more complex setup, as the victim must fine-tune the retriever using the attacker poisoned dataset.
Open AccessBackdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
Large Language Models (LLMs) have demonstrated remarkable capabilities in generating coherent text but remain limited by the static nature of their training data. Retrieval Augmented Generation (RAG) addresses this issue by combining LLMs with up-to-date information retrieval, but also expand the attack surface of the system. This paper investigates prompt injection attacks on RAG, focusing on malicious objectives beyond misinformation, such as inserting harmful links, promoting unauthorized services, and initiating denial-of-service behaviors. We build upon existing corpus poisoning techniques and propose a novel backdoor attack aimed at the fine-tuning process of the dense retriever component. Our experiments reveal that corpus poisoning can achieve significant attack success rates through the injection of a small number of compromised documents into the retriever corpus. In contrast, backdoor attacks demonstrate even higher success rates but necessitate a more complex setup, as the victim must fine-tune the retriever using the attacker poisoned dataset.
- Open Access
- 27 December 2022
- Published by MDPI AG in Journal of Low Power Electronics and Applications
- Vol. 13 (1) , 1
CCALK: (When) CVA6 Cache Associativity Leaks the Key
In this work, we study an end-to-end implementation of a Prime + Probe covert channel on the CVA6 RISC-V processor implemented on a FPGA target and running a Linux OS. We develop the building blocks of the covert channel and provide a detailed view of its behavior and effectiveness. We propose a realistic scenario for extracting information of an AES-128 encryption algorithm implementation. Throughout this work, we discuss the challenges brought by the presence of a running OS while carrying out a micro architectural covert channel. This includes the effects of having other running processes, unwanted cache evictions and the OS’ timing behavior. We also propose an analysis of the relationship between the data cache’s characteristics and the developed covert channel’s capacity to extract information. According to the results of our experimentations, we present guidelines on how to build and configure a micro architectural covert channel resilient cache in a mono-core mono-thread scenario.
- 27 December 2022
- Published by MDPI AG in Journal of Low Power Electronics and Applications
- Vol. 13 (1) , 1
Open AccessCCALK: (When) CVA6 Cache Associativity Leaks the Key
In this work, we study an end-to-end implementation of a Prime + Probe covert channel on the CVA6 RISC-V processor implemented on a FPGA target and running a Linux OS. We develop the building blocks of the covert channel and provide a detailed view of its behavior and effectiveness. We propose a realistic scenario for extracting information of an AES-128 encryption algorithm implementation. Throughout this work, we discuss the challenges brought by the presence of a running OS while carrying out a micro architectural covert channel. This includes the effects of having other running processes, unwanted cache evictions and the OS’ timing behavior. We also propose an analysis of the relationship between the data cache’s characteristics and the developed covert channel’s capacity to extract information. According to the results of our experimentations, we present guidelines on how to build and configure a micro architectural covert channel resilient cache in a mono-core mono-thread scenario.
- Open Access
CVA6's Data cache: Structure and Behavior
Since Spectre and Meltdown's disclosure in 2018, a new category of attacks has been identified and characterized by the scientific community. The Foreshadow attack, which was the first one to target Intel's secure enclave technology (namely SGX) has been developed shortly after. It opened the way to micro architectural attacks on Intel's architecture, and led to the quick development of micro architectural attacks until today. While Spectre and Meltdown are often considered as the first micro architectural attacks, one can argue that cache attacks, as introduced by Osvik et al. in 2006, can be seen as the first types of micro architectural attacks that were developed. Now, even though there are many variants, they are still the most prominent type of micro architectural attacks. One example of cache micro architectural covert-channel is the Prime+Probe. Lately targeting the Intel architecture, the micro architectural attacks are now challenging a wider variety of CPUs. Recently, CPUs running the RISC-V Instruction Set Architecture have been targeted. One famous and widely used RISC-V CPU is the ETH Zurich's CVA6 (formerly Ariane) core. CVA6 is a 6-stage, single issue, in-order CPU. To the best of our knowledge, there is no existing document presenting very detailed aspects of the CVA6's micro architecture, especially with respect to the data cache. Such information is mandatory to deeply understand any architectural or micro architectural study successfully, such as the replication of the Prime+Probe attack on the CVA6 CPU proposed by Nils Wistoff. This paper presents the implementation of the Data cache in the CVA6 CPU from OpenHW Group by focusing on its memory structure and explaining through several examples what happens when a request for memory allocation occurs.
Open AccessCVA6's Data cache: Structure and Behavior
Since Spectre and Meltdown's disclosure in 2018, a new category of attacks has been identified and characterized by the scientific community. The Foreshadow attack, which was the first one to target Intel's secure enclave technology (namely SGX) has been developed shortly after. It opened the way to micro architectural attacks on Intel's architecture, and led to the quick development of micro architectural attacks until today. While Spectre and Meltdown are often considered as the first micro architectural attacks, one can argue that cache attacks, as introduced by Osvik et al. in 2006, can be seen as the first types of micro architectural attacks that were developed. Now, even though there are many variants, they are still the most prominent type of micro architectural attacks. One example of cache micro architectural covert-channel is the Prime+Probe. Lately targeting the Intel architecture, the micro architectural attacks are now challenging a wider variety of CPUs. Recently, CPUs running the RISC-V Instruction Set Architecture have been targeted. One famous and widely used RISC-V CPU is the ETH Zurich's CVA6 (formerly Ariane) core. CVA6 is a 6-stage, single issue, in-order CPU. To the best of our knowledge, there is no existing document presenting very detailed aspects of the CVA6's micro architecture, especially with respect to the data cache. Such information is mandatory to deeply understand any architectural or micro architectural study successfully, such as the replication of the Prime+Probe attack on the CVA6 CPU proposed by Nils Wistoff. This paper presents the implementation of the Data cache in the CVA6 CPU from OpenHW Group by focusing on its memory structure and explaining through several examples what happens when a request for memory allocation occurs.