105 citations · 501 across the 65 of their papers we have counts for
9 papers · 1 filter
Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
Bronislav Sidik, Lior Rokach
Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives t…
Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
Tzvi Lederer, Gallil Maimon, Lior Rokach
Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that o…
PrivGen: Preserving Privacy of Sequences Through Data Generation
Sigal Shaked, Lior Rokach
Sequential data is everywhere, and it can serve as a basis for research that will lead to improved processes. For example, road infrastructure can be improved by identifying bottle…
Defense Methods Against Adversarial Examples for Recurrent Neural Networks
Ishai Rosenberg, Asaf Shabtai, Yuval Elovici +1
Adversarial examples are known to mislead deep learning models to incorrectly classify them, even in domains where such models achieve state-of-the-art performance. Until recently,…
Query-Efficient Black-Box Attack Against Sequence-Based Malware Classifiers
Ishai Rosenberg, Asaf Shabtai, Yuval Elovici +1
In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers. We generate adversarial examples by modifying the…
Sampling High Throughput Data for Anomaly Detection of Data-Base Activity
Hagit Grushka-Cohen, Oded Sofer, Ofer Biller +3
Data leakage and theft from databases is a dangerous threat to organizations. Data Security and Data Privacy protection systems (DSDP) monitor data access and usage to identify lea…