Publications

Academic Articles

PRISM: Recovering Instruction Sets from Language Model Activations. Gilad Gressel, Rahul Pankajakshan, Julia Diament, Efim Hudis, Krishnashree Achuthan, Yisroel Mirsky. EMNLP 2026. Rank A* Project page →
Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents. Or Zion Eliav, Eyal Lenga, Shir Bernstein, Yisroel Mirsky. ACSAC 2026. Rank A Project page →
Love, Lies, and Language Models: Investigating AI’s Role in Romance-Baiting Scams. Gilad Gressel, Rahul Pankajakshan, Shir Rozenfeld, Ling Li, Ivan Franceschini, Krishnashree Achuthan, Yisroel Mirsky. USENIX Security 2026. Rank A* Runner-up Distinguished Paper Award Project page →
GAVEL: Towards rule-based safety through activation monitoring. Shir Rozenfeld, Rahul Pankajakshan, Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky. ICLR 2026. Rank A* Project page →
Memory Backdoor Attacks on Neural Networks. Eden Luzon, Roy Weiss, Torsten Krauss, Alexandra Dimitrienko, Yisroel Mirsky. NDSS 2026. Rank A*
Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias Shir Bernstein, David Beste, Daniel Ayzenshteyn, Lea Schönherr, Yisroel Mirsky. NDSS 2026. Rank A* Project page →
Boundary Sampling for Efficient Model Extraction Doron Ben Chayim, Maor Biton Dor, Eyal Lenga, Yisroel Mirsky. ACM TIST. 2026 Rank Q1
Cloak, Honey, Trap: Proactive Defenses Against LLM Agents D Ayzenshteyn, R Weiss, Y Mirsky. USENIX Security 2025 Rank A* Project page →
The Threat of Deepfake Fingerprints Y Hacmon, K Gorelik, Y Mirsky. WDC, 2025 Best Paper Award
PEAS: A Strategy for Crafting Transferable Adversarial Examples B Avraham, Y Mirsky. ACM TIST. 2025 Rank Q1.‏
Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks R Bokobza, Y Mirsky. ACM TIST. 2025 Rank Q1‏
What Was Your Prompt? A Remote Keylogging Attack on AI Assistants R Weiss, D Ayzenshteyn, G Amit, Y Mirsky. USENIX Security 2024 Rank A* & DEF CON 32.
Efficient Model Extraction via Boundary Sampling Maor Biton Dor, Yisroel Mirsky. ACM AISec, 2024 Best Paper Award
Exploiting LLMs for Scam Automation: A Looming Threat G Gressel, R Pankajakshan, Y Mirsky. WDC, 2024 Best Paper Award
Transpose Attack: Stealing Datasets with Bidirectional Training Guy Amit, Moshe Levy, Yisroel Mirsky. NDSS, 2024. Rank A*
VulChecker: Graph-based Vulnerability Localization in Source Code Yisroel Mirsky, George Macon, Michael Brown, Carter Yagemann, Matthew Pruett, Evan Downing, Sukarno Mertoguno, Wenke Lee. USENIX Security Symposium, 2023. Rank A*
Deepfake CAPTCHA: A Method for Preventing Fake Calls Lior Yasur, Guy Frankovits, Fred M Grabovski, Yisroel Mirsky. ASIA CCS 2023. Rank A
The Threat of Offensive AI to Organizations Yisroel Mirsky, Ambra Demontis, Jaidip Kotak, Ram Shankar, Deng Gelei, Liu Yang, Xiangyu Zhang, Maura Pintor, Wenke Lee, Yuval Elovici, Battista Biggio. Computers & Security 2022. IF 5.1, 34/246, Q1
DeepReflect: Discovering Malicious Functionality through Binary Reconstruction Evan Downing, Yisroel Mirsky, Kyuhong Park, and Wenke Lee. USENIX Security Symposium, 2021. Rank A*
Attacking Tesla Model Xs Autopilot Using Compromised Advertisement Ben Nassi, Yisroel Mirsky, Dudi Nassi, Raz Ben-Netanel, Oleg Drokin, and Yuval Elovici. Workshop on Automotive and Autonomous Vehicle Security (AutoSec), 2021. Co-located with NDSS.
The Creation and Detection of Deepfakes: A Survey Yisroel Mirsky, and Wenke Lee. ACM Computing Surveys (CSUR), 2020. Rank Q1
Phantom of the ADAS: Securing Advanced Driver-Assistance Systems from Split-Second Phantom Attacks Ben Nassi, Yisroel Mirsky, Dudi Nassi, Raz Ben-Netanel, Oleg Drokin, and Yuval Elovici. ACM Conference on Computer and Communications Security (CCS), 2020. Rank A*
CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning Yisroel Mirsky, Tom Mahler, Ilan Shelef, and Yuval Elovici. USENIX Security Symposium, 2019. Rank A*
DICOM images have been hacked! Now what? Benoit Desjardins, Yisroel Mirsky, Markel Picado Ortiz, Zeev Glozmand, Lawrence Tarbox, Robert Hornf, and Steven C. Horii. American Roentgen Ray Society (ARRS), American Journal of Roentgenology (AJR), 2019. Rank Q1