Ankit Gangwal
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
Ankit Gangwal has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Mauro Conti
University of Padova, Padova, Italy, and Örebro University, Örebro, Sweden
13 shared publications Manoj Singh Gaur
Department of Computer Science & Engineering, Malaviya National Institute of Technology, India
3 shared publications- Abhijeet Srivastava
International Institute of Information Technology
2 shared publications Apoorva Thirupathi
2 shared publicationsHaripriya Ravali Gangavalli
2 shared publicationsMauro Conti
Department of Mathematics, University of Padua, Italy
2 shared publications
Latest Publications
- 30 October 2026
- Published by Springer Nature
- p. 508-538
Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability
- 30 October 2026
- Published by Springer Nature
- p. 508-538
Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability
- 13 October 2025
- Published by Springer Nature
- p. 126-146
KeTS: Kernel-Based Trust Segmentation Against Model Poisoning Attacks
- 13 October 2025
- Published by Springer Nature
- p. 126-146
KeTS: Kernel-Based Trust Segmentation Against Model Poisoning Attacks
- Open Access
Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
Model Merging (MM) has emerged as a promising alternative to multi-task learning, where multiple fine-tuned models are combined, without access to tasks' training data, into a single model that maintains performance across tasks. Recent works have explored the impact of MM on adversarial attacks, particularly backdoor attacks. However, none of them have sufficiently explored its impact on transfer attacks using adversarial examples, i.e., a black-box adversarial attack where examples generated for a surrogate model successfully mislead a target model. In this work, we study the effect of MM on the transferability of adversarial examples. We perform comprehensive evaluations and statistical analysis consisting of 8 MM methods, 7 datasets, and 6 attack methods, sweeping over 336 distinct attack settings. Through it, we first challenge the prevailing notion of MM conferring free adversarial robustness, and show MM cannot reliably defend against transfer attacks, with over 95% relative transfer attack success rate. Moreover, we reveal 3 key insights for machine-learning practitioners regarding MM and transferability for a robust system design: (1) stronger MM methods increase vulnerability to transfer attacks; (2) mitigating representation bias increases vulnerability to transfer attacks; and (3) weight averaging, despite being the weakest MM method, is the most vulnerable MM method to transfer attacks. Finally, we analyze the underlying reasons for this increased vulnerability, and provide potential solutions to the problem. Our findings offer critical insights for designing more secure systems employing MM.
Open AccessMerge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
Model Merging (MM) has emerged as a promising alternative to multi-task learning, where multiple fine-tuned models are combined, without access to tasks' training data, into a single model that maintains performance across tasks. Recent works have explored the impact of MM on adversarial attacks, particularly backdoor attacks. However, none of them have sufficiently explored its impact on transfer attacks using adversarial examples, i.e., a black-box adversarial attack where examples generated for a surrogate model successfully mislead a target model. In this work, we study the effect of MM on the transferability of adversarial examples. We perform comprehensive evaluations and statistical analysis consisting of 8 MM methods, 7 datasets, and 6 attack methods, sweeping over 336 distinct attack settings. Through it, we first challenge the prevailing notion of MM conferring free adversarial robustness, and show MM cannot reliably defend against transfer attacks, with over 95% relative transfer attack success rate. Moreover, we reveal 3 key insights for machine-learning practitioners regarding MM and transferability for a robust system design: (1) stronger MM methods increase vulnerability to transfer attacks; (2) mitigating representation bias increases vulnerability to transfer attacks; and (3) weight averaging, despite being the weakest MM method, is the most vulnerable MM method to transfer attacks. Finally, we analyze the underlying reasons for this increased vulnerability, and provide potential solutions to the problem. Our findings offer critical insights for designing more secure systems employing MM.
- Open Access
- 24 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1812-1814
POSTER: Investigating Transferability of Adversarial Examples in Model Merging
- 24 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1812-1814
Open AccessPOSTER: Investigating Transferability of Adversarial Examples in Model Merging
- Open Access
- 24 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1794-1796
POSTER: Disappearing Ink: How Partial Model Extraction Erases Watermarks
- 24 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1794-1796
Open AccessPOSTER: Disappearing Ink: How Partial Model Extraction Erases Watermarks
- Open Access
- 31 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 376-385
Attacking Anonymity Set in Tornado Cash via Wallet Fingerprints
- 31 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 376-385
Open AccessAttacking Anonymity Set in Tornado Cash via Wallet Fingerprints
- Open Access
- 31 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1780-1789
Swiss Cheese CAPTCHA: A Novel Multi-barrier Mechanism for Bot Detection
- 31 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1780-1789
Open AccessSwiss Cheese CAPTCHA: A Novel Multi-barrier Mechanism for Bot Detection
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (3) , 2705-2722
SharHSC: A Sharding-Based Hybrid State Channel to Realize Blockchain Scalability and Security
Addressing blockchain's insufficient throughput and scalability is imperative for practical viability. Off-chain approaches, such as state channels (including Hash Time Lock Contract (HTLC), virtual channels), demonstrate enhanced throughput by enabling parallel transaction processing. While virtual channels introduce execution complexity, HTLC suffers from high update delays. Moreover, existing methods face network attacks. We present Sharding-based Hybrid State Channel (SharHSC) to address these issues. Firstly, we introduce a novel off-chain sharding architecture, which partitions proxy nodes into multiple shards. Thus, when the off-chain node count increases, adding shards enhances system throughput. Secondly, each shard establishes a supervisory committee to record latest channel statuses to ensure accurate fund distribution upon channel closure. Thirdly, we combine the strengths of HTLC and virtual channels. In particular, SharHSC constructs a single virtual channel across all the nodes involved in the payment by treating the nodes between payer and payee as an intermediate entity, which utilizes HTLC for fund routing. This realizes both low latency and streamlined complexity. Finally, our work is substantiated by security analysis and experiments. As the node number varies, compared with HTLC and virtual channels, the latency is reduced by 49.32% and 31.82%, and the throughput is increased by 8.93 and 1.89 times.
- 23 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (3) , 2705-2722
SharHSC: A Sharding-Based Hybrid State Channel to Realize Blockchain Scalability and Security
Addressing blockchain's insufficient throughput and scalability is imperative for practical viability. Off-chain approaches, such as state channels (including Hash Time Lock Contract (HTLC), virtual channels), demonstrate enhanced throughput by enabling parallel transaction processing. While virtual channels introduce execution complexity, HTLC suffers from high update delays. Moreover, existing methods face network attacks. We present Sharding-based Hybrid State Channel (SharHSC) to address these issues. Firstly, we introduce a novel off-chain sharding architecture, which partitions proxy nodes into multiple shards. Thus, when the off-chain node count increases, adding shards enhances system throughput. Secondly, each shard establishes a supervisory committee to record latest channel statuses to ensure accurate fund distribution upon channel closure. Thirdly, we combine the strengths of HTLC and virtual channels. In particular, SharHSC constructs a single virtual channel across all the nodes involved in the payment by treating the nodes between payer and payee as an intermediate entity, which utilizes HTLC for fund routing. This realizes both low latency and streamlined complexity. Finally, our work is substantiated by security analysis and experiments. As the node number varies, compared with HTLC and virtual channels, the latency is reduced by 49.32% and 31.82%, and the throughput is increased by 8.93 and 1.89 times.
- Open Access
- 19 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 28225-28234
De-Authentication Using Ambient Light Sensor
While user authentication happens before initiating or resuming a login session, de-authentication detects the absence of a previously-authenticated user to revoke her currently active login session. The absence of proper de-authentication can lead to well-known lunchtime attacks, where a nearby adversary takes over a carelessly departed user’s running login session. The existing solutions for automatic de-authentication have distinct practical limitations, e.g., extraordinary deployment requirements or high initial cost of external equipment. In this paper, we propose “DE-authentication using Ambient Light sensor” (DEAL), a novel, inexpensive, fast, and user-friendly de-authentication approach. DEAL utilizes the built-in ambient light sensor of a modern computer to determine if the user is leaving her work-desk. DEAL, by design, is resilient to natural shifts in lighting conditions and can be configured to handle abrupt changes in ambient illumination (e.g., due to toggling of room lights). We collected data samples from 4800 sessions with 120 volunteers in 4 typical workplace settings and conducted a series of experiments to evaluate the quality of our proposed approach thoroughly. Our results show that DEAL can de-authenticate a departing user within 4 seconds with a hit rate of 89.15% and a fall-out of 7.35%. Finally, bypassing DEAL to launch a lunchtime attack is practically infeasible as it requires the attacker to either take the user’s position within a few seconds or manipulate the sensor readings sophisticatedly in real-time.
- 19 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 28225-28234
Open AccessDe-Authentication Using Ambient Light Sensor
While user authentication happens before initiating or resuming a login session, de-authentication detects the absence of a previously-authenticated user to revoke her currently active login session. The absence of proper de-authentication can lead to well-known lunchtime attacks, where a nearby adversary takes over a carelessly departed user’s running login session. The existing solutions for automatic de-authentication have distinct practical limitations, e.g., extraordinary deployment requirements or high initial cost of external equipment. In this paper, we propose “DE-authentication using Ambient Light sensor” (DEAL), a novel, inexpensive, fast, and user-friendly de-authentication approach. DEAL utilizes the built-in ambient light sensor of a modern computer to determine if the user is leaving her work-desk. DEAL, by design, is resilient to natural shifts in lighting conditions and can be configured to handle abrupt changes in ambient illumination (e.g., due to toggling of room lights). We collected data samples from 4800 sessions with 120 volunteers in 4 typical workplace settings and conducted a series of experiments to evaluate the quality of our proposed approach thoroughly. Our results show that DEAL can de-authenticate a departing user within 4 seconds with a hit rate of 89.15% and a fall-out of 7.35%. Finally, bypassing DEAL to launch a lunchtime attack is practically infeasible as it requires the attacker to either take the user’s position within a few seconds or manipulate the sensor readings sophisticatedly in real-time.
- 10 August 2023
- Published by Springer Nature
- p. 75-108
Bitcoin Blockchain System: An Overview of Security and Privacy Aspects
- 10 August 2023
- Published by Springer Nature
- p. 75-108
Bitcoin Blockchain System: An Overview of Security and Privacy Aspects