8 papers
Parser-Free Querying of Security Logs
Evan Luo, Julien Piet, David Wagner
Security analysts routinely query system logs to detect threats and investigate incidents, but each log source uses its own semi-structured format: logs are cheap to produce, but e…
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
Debeshee Das, Julien Piet, Darya Kaviani +3
Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack,…
Web Agents Should Adopt the Plan-Then-Execute Paradigm
Julien Piet, Annabella Chow, Yiwei Hou +5
ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web a…
Semantic-Aware Parsing for Security Logs
Julien Piet, Vivian Fang, Rishi Khare +4
Security logs are foundational to threat detection and post-incident investigation, yet analysts often struggle to fully leverage them due to their heterogeneity and unstructured n…
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
Julien Piet, Xiao Huang, Dennis Jacob +7
Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulne…
Toxicity Detection for Free
Zhanhao Hu, Julien Piet, Geng Zhao +2
Current LLMs are generally aligned to follow safety requirements and tend to refuse toxic prompts. However, LLMs can fail to refuse toxic prompts or be overcautious and refuse beni…