6 papers
AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
Zijie Zhao, Chenyuan Yang, Weidong Wang +3
While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, limiting the practicality of a…
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
Hwiwon Lee, Jiawei Liu, Dongjun Kim +4
Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC)…
AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
Che Wang, Jiaming Zhang, Ziqi Zhang +6
The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However,…
ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
Che Wang, Fuyao Zhang, Jiaming Zhang +6
Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existi…
SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
Hwiwon Lee, Ziqi Zhang, Hanxiao Lu +1
Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycl…
Membership and Memorization in LLM Knowledge Distillation
Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu +2
Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ''teacher'' to…