Roman Vainshtein

According to our database, Roman Vainshtein authored at least 29 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

When Scanners Lie: Evaluator Instability in LLM Red-Teaming.

Lidor Erez, Omer Hofman, Tamir Nizri, Roman Vainshtein

CoRR, March, 2026

Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG.

Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni, Roman Vainshtein, Andrés F. Murillo, Hisashi Kojima, Motoyoshi Sekiya, Yuki Unno, Junichi Suga

CoRR, February, 2026

Inference-Time Backdoors via Hidden Instructions in LLM Chat Templates.

Ariel Fogel, Omer Hofman, Eilon Cohen, Roman Vainshtein

CoRR, February, 2026

AgenTRIM: Tool Risk Mitigation for Agentic AI.

Roy Betser, Shamik Bose, Amit Giloni, Chiara Picardi, Sindhu Padakandla, Roman Vainshtein

CoRR, January, 2026

Training-free Detection of Text-to-video Generations via Over-coherence.

Jonathan Brokman, Oren Rachmil, Omer Hofman, Roy Betser, Amit Giloni, Roman Vainshtein, Hisashi Kojima

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood.

Roy Betser, Omer Hofman, Roman Vainshtein, Guy Gilboa

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

MAPS: A Multilingual Benchmark for Agent Performance and Security.

Omer Hofman, Jonathan Brokman, Oren Rachmil, Shamik Bose, Vikas Pahuja, Toshiya Shimizu, Trisha Starostina, Kelly Marchisio, Seraphina Goldfarb-Tarrant, Roman Vainshtein

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

2025

Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs.

Oren Rachmil, Roy Betser, Itay Gershon, Omer Hofman, Nitay Yakoby, Yuval Meron, Idan Yankelev, Asaf Shabtai, Yuval Elovici, Roman Vainshtein

CoRR, December, 2025

Counterfactual-based Agent Influence Ranker for Agentic AI Workflows.

Amit Giloni, Chiara Picardi, Roy Betser, Shamik Bose, Aishvariya Priya Rathina Sabapathy, Roman Vainshtein

CoRR, October, 2025

MAPS: A Multilingual Benchmark for Global Agent Performance and Security.

Omer Hofman, Oren Rachmil, Shamik Bose, Vikas Pahuja, Jonathan Brokman, Toshiya Shimizu, Trisha Starostina, Kelly Marchisio, Seraphina Goldfarb-Tarrant, Roman Vainshtein

CoRR, May, 2025

Identifying Memorization of Diffusion Models Through p-Laplace Analysis.

Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa

Proceedings of the Scale Space and Variational Methods in Computer Vision, 2025

Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis.

Jonathan Brokman, Omer Hofman, Oren Rachmil, Inderjeet Singh, Vikas Pahuja, Rathina Sabapathy, Aishvariya Priya, Amit Giloni, Roman Vainshtein, Hisashi Kojima

Proceedings of the IEEE/ACM International Workshop on Responsible AI Engineering, 2025

Gradient Inversion of Multimodal Models.

Omri Ben Hemo, Alon Zolfi, Oryan Yehezkel, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Yuval Elovici, Asaf Shabtai

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images.

Jonathan Brokman, Amit Giloni, Omer Hofman, Roman Vainshtein, Hisashi Kojima, Guy Gilboa

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

TFDP: Token-Efficient Disparity Audits for Autoregressive LLMs via Single-Token Masked Evaluation.

Inderjeet Singh, Ramya Srinivasan, Roman Vainshtein, Hisashi Kojima

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

CAIR: Counterfactual-based Agent Influence Ranker for Agentic AI Workflows.

Amit Giloni, Chiara Picardi, Roy Betser, Shamik Bose, Aishvariya Priya Rathina Sabapathy, Roman Vainshtein

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Automated algorithm selection using meta-learning and pre-trained deep convolution neural networks.

Itai Dagan, Roman Vainshtein, Gilad Katz, Lior Rokach

Inf. Fusion, May, 2024

The Branch Not Taken: Predicting Branching in Online Conversations.

Shai Meital, Lior Rokach, Roman Vainshtein, Nir Grinberg

CoRR, 2024

MONTRAGE: Monitoring Training for Attribution of Generative Diffusion Models.

Jonathan Brokman, Omer Hofman, Roman Vainshtein, Amit Giloni, Toshiya Shimizu, Inderjeet Singh, Oren Rachmil, Alon Zolfi, Asaf Shabtai, Yuki Unno, Hisashi Kojima

Proceedings of the Computer Vision - ECCV 2024, 2024

ATLANTIS: A Framework for Automated Targeted Language-guided Augmentation Training for Robust Image Search.

Inderjeet Singh, Roman Vainshtein, Alon Zolfi, Asaf Shabtai, Tu Bui, Jonathan Brokman, Omer Hofman, Fumiyoshi Kasahara, Kentaro Tsuji, Hisashi Kojima

Proceedings of the 35th British Machine Vision Conference, 2024

2023

DeepCAN: Hybrid Method for Road Type Classification Using Vehicle Sensor Data for Smart Autonomous Mobility.

Adva Hadrian, Roman Vainshtein, Bracha Shapira, Lior Rokach

IEEE Trans. Intell. Transp. Syst., November, 2023

2020

Automatic Machine Learning Derived from Scholarly Big Data.

Asnat Greenstein-Messica, Roman Vainshtein, Gilad Katz, Bracha Shapira, Lior Rokach

CoRR, 2020

Sequence Preserving Network Traffic Generation.

Sigal Shaked, Amos Zamir, Roman Vainshtein, Moshe Unger, Lior Rokach, Rami Puzis, Bracha Shapira

CoRR, 2020

DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering.

Yuval Heffetz, Roman Vainshtein, Gilad Katz, Lior Rokach

Proceedings of the KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2020

MetaTPOT: Enhancing A Tree-based Pipeline Optimization Tool Using Meta-Learning.

Doron Laadan, Roman Vainshtein, Yarden Curiel, Gilad Katz, Lior Rokach

Proceedings of the CIKM '20: The 29th ACM International Conference on Information and Knowledge Management, 2020

2019

RankML: a Meta Learning-Based Approach for Pre-Ranking Machine Learning Pipelines.

Doron Laadan, Roman Vainshtein, Yarden Curiel, Gilad Katz, Lior Rokach

CoRR, 2019

Assessing the Quality of Scientific Papers.

Roman Vainshtein, Gilad Katz, Bracha Shapira, Lior Rokach

CoRR, 2019

AutoGRD: Model Recommendation Through Graphical Dataset Representation.

Noy Cohen-Shapira, Lior Rokach, Bracha Shapira, Gilad Katz, Roman Vainshtein

Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019

2018

A Hybrid Approach for Automatic Model Recommendation.

Roman Vainshtein, Asnat Greenstein-Messica, Gilad Katz, Bracha Shapira, Lior Rokach

Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018