4 papers
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie +2
Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense me…
LLM-Based Penetration Testing in the Presence of Honeypots
Xinhong Xie, Piyush Nagasubramaniam, Neeraj Karamchandani +1
Large language model (LLM) agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. Th…
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
Neeraj Karamchandani, Piyush Nagasubramaniam, Sencun Zhu +1
Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this ha…
Prompting Forgetting: Unlearning in GANs via Textual Guidance
Piyush Nagasubramaniam, Neeraj Karamchandani, Chen Wu +1
State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Conse…