7 papers
Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents
Sidharth Pulipaka, Ansh Sharma, Stanislau Hlebik +4
Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and create persistent artifacts. A…
Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return
Arham Sethi, Arsen Kenzhebayev, Saanvi Paturi +3
Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply one. We isolate this post-failu…
When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering
Saanvi Paturi, Arsen Kenzhebayev, Arham Sethi +3
Large language models (LLMs) are increasingly deployed with external tools that extend what they can do beyond their own knowledge. Tools help on tasks that need external informati…
Multi-View Decompilation for LLM-Based Malware Classification
Bercan Turkmen, Vyas Raina
Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can assist thi…
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
Sidharth Pulipaka, Stanislau Hlebik, Leonidas Raghav +4
Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity.…
PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
Sidharth Pulipaka, Oliver Chen, Manas Sharma +3
Conversational assistants are increasingly integrating long-term memory with large language models (LLMs). This persistence of memories, e.g., the user is vegetarian, can enhance p…
Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs
Arya Labroo, Ivaxi Sheth, Vyas Raina +2
Large Language Models (LLMs) offer strong generative capabilities, but many applications require explicit and \textit{fine-grained} control over specific textual concepts, such as…