collaborators

5 papers

cs.CR2026

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

Chong Xiang, Drew Zagieboylo, Shaona Ghosh +5

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigge…

cs.CR2026

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

Yuqi Jia, Ruiqi Wang, Xilong Wang +2

Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typic…

cs.CR2026

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis

Peiran Wang, Xinfeng Li, Chong Xiang +5

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilitie…

cs.CR2026

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models

Xiaogeng Liu, Xinyan Wang, Yechao Zhang +5

Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time de…

cs.CR2025

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis

Mintong Kang, Chong Xiang, Sanjay Kariyappa +3

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In t…