Omer Hofman

20 papers A* 3A 2Journal 10Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Inference-Time Backdoors via Hidden Instructions in LLM Chat Templates.
CoRR
Ariel Fogel, Omer Hofman, Eilon Cohen, Roman Vainshtein
2026 — conf
MAPS: A Multilingual Benchmark for Agent Performance and Security.
EACL (Findings)
Omer Hofman, Jonathan Brokman, Oren Rachmil, Shamik Bose, Vikas Pahuja, Toshiya Shimizu, Trisha Starostina, Kelly Marchisio, Seraphina Goldfarb-Tarrant, Roman Vainshtein
2026 J jnl
When Scanners Lie: Evaluator Instability in LLM Red-Teaming.
CoRR
Lidor Erez, Omer Hofman, Tamir Nizri, Roman Vainshtein
2025 — conf
DIESEL: A Lightweight Inference-Time Safety Enhancement for Language Models.
ACL (Findings)
Ben Ganon, Alon Zolfi, Omer Hofman, Inderjeet Singh, Hisashi Kojima, Yuval Elovici, Asaf Shabtai
2025 A conf
DiL: An Explainable and Practical Metric for Abnormal Uncertainty in Object Detection.
WACV
Amit Giloni, Omer Hofman, Ikuya Morikawa, Toshiya Shimizu, Yuval Elovici, Asaf Shabtai
2025 A* conf
Gradient Inversion of Multimodal Models.
ICML
Omri Ben Hemo, Alon Zolfi, Oryan Yehezkel, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Yuval Elovici, Asaf Shabtai
2025 — conf
Identifying Memorization of Diffusion Models Through p-Laplace Analysis.
SSVM (1)
Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa
2025 J jnl
Identifying Memorization of Diffusion Models through p-Laplace Analysis.
CoRR
Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa
2025 — conf
Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis.
RAIE
Jonathan Brokman, Omer Hofman, Oren Rachmil, Inderjeet Singh, Vikas Pahuja, Rathina Sabapathy, Aishvariya Priya, Amit Giloni, Roman Vainshtein, Hisashi Kojima
2025 A* conf
KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models.
AAAI
Yarin Yerushalmi Levi, Edita Grolman, Idan Yankelev, Amit Giloni, Omer Hofman, Toshiya Shimizu, Asaf Shabtai, Yuval Elovici
2025 J jnl
MAPS: A Multilingual Benchmark for Global Agent Performance and Security.
CoRR
Omer Hofman, Oren Rachmil, Shamik Bose, Vikas Pahuja, Jonathan Brokman, Toshiya Shimizu, Trisha Starostina, Kelly Marchisio, Seraphina Goldfarb-Tarrant, Roman Vainshtein
2025 A* conf
Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images.
ICLR
Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa
2025 J jnl
Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images.
CoRR
Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa
2025 J jnl
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs.
CoRR
Oren Rachmil, Roy Betser, Itay Gershon, Omer Hofman, Nitay Yakoby, Yuval Meron, Idan Yankelev, Asaf Shabtai, Yuval Elovici, Roman Vainshtein
2024 A conf
ATLANTIS: A Framework for Automated Targeted Language-guided Augmentation Training for Robust Image Search.
BMVC
Inderjeet Singh, Roman Vainshtein, Alon Zolfi, Asaf Shabtai, Tu Bui, Jonathan Brokman, Omer Hofman, Fumiyoshi Kasahara, Kentaro Tsuji, Hisashi Kojima
2024 J jnl
DIESEL - Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs.
CoRR
Ben Ganon, Alon Zolfi, Omer Hofman, Inderjeet Singh, Hisashi Kojima, Yuval Elovici, Asaf Shabtai
2024 J jnl
Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis.
CoRR
Jonathan Brokman, Omer Hofman, Oren Rachmil, Inderjeet Singh, Rathina Sabapathy, Aishvariya Priya, Vikas Pahuja, Amit Giloni, Roman Vainshtein, Hisashi Kojima
2024 — conf
MONTRAGE: Monitoring Training for Attribution of Generative Diffusion Models.
ECCV (75)
Jonathan Brokman, Omer Hofman, Roman Vainshtein, Amit Giloni, Toshiya Shimizu, Inderjeet Singh, Oren Rachmil, Alon Zolfi, Asaf Shabtai, Yuki Unno, Hisashi Kojima
2024 J jnl
X-Detect: explainable adversarial patch detection for object detectors in retail.
Mach. Learn.
Omer Hofman, Amit Giloni, Yarin Hayun, Ikuya Morikawa, Toshiya Shimizu, Yuval Elovici, Asaf Shabtai
2023 J jnl
X-Detect: Explainable Adversarial Patch Detection for Object Detectors in Retail.
CoRR
Omer Hofman, Amit Giloni, Yarin Hayun, Ikuya Morikawa, Toshiya Shimizu, Yuval Elovici, Asaf Shabtai