activity
20242026
collaborators

8 papers

cs.CR2026

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Pengfei He, Lesly Miculicich, Vishesh Sharma +5

Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt in…

cs.LG2026

LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra +6

As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete de…

cs.CR2026

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

Minbeom Kim, Mihir Parmar, Phillip Wallis +5

AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted co…

cs.LG2026

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

Pengfei He, Ash Fox, Lesly Miculicich +7

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to li…

cs.LG2025

Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models

Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar +7

Pre-trained Time Series Foundational Models (TSFMs) represent a significant advance, capable of forecasting diverse time series with complex characteristics, including varied seaso…

cs.SE2025

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation

Lesly Miculicich, Mihir Parmar, Hamid Palangi +4

The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user obje…