5 papers
Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents
Tobias Kaiser, Tobias Kaisar, Aritra Dhar
Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows t…
Can LLMs Make (Personalized) Access Control Decisions?
Friederike Groschupp, Daniele Lain, Aritra Dhar +2
Precise access control decisions are crucial for the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during…
RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations
Aritra Dhar, Vasilije Stambolic, Lukas Cavigelli
Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It do…
AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs
Lara Magdalena Lazier, Aritra Dhar, Vasilije Stambolic +1
Corporate LLMs are gaining traction for efficient knowledge dissemination and management within organizations. However, as current LLMs are vulnerable to leaking sensitive informat…
Ascend-CC: Confidential Computing on Heterogeneous NPU for Emerging Generative AI Workloads
Aritra Dhar, Clément Thorens, Lara Magdalena Lazier +1
Cloud workloads have dominated generative AI based on large language models (LLM). Specialized hardware accelerators, such as GPUs, NPUs, and TPUs, play a key role in AI adoption d…