arXiv AI

AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

arXiv Machine Learning
Sep 11

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents

DriftNet is a dual‑head trajectory Transformer designed to detect and localize prompt injection attacks in large language model agents. It processes logged tool‑call trajectories, classifying each as compromised or not while labeling every step as benign, injection point, hijacked, or failed injection. On the AgentDrift benchmark, DriftNet achieves high accuracy, with an F1 score of 0.983, 98.7% exact injection‑point recovery, and low false‑alarm rates.

By Asif Pinjari, Mithun Paul Saint-Germain
arXiv AI
Jun 12

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.

By Zihao Wang, Yiming Li, Yutong Wu, Zheyu Liu, Kangjie Chen, Fok Kar Wai, Pin-Yu Chen, Vrizlynn L. L. Thing, Bo Li, Dacheng Tao, Tianwei Zhang
arXiv AI
Aug 28

How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation

The paper introduces CTF-ABACUS, a trace-based auditing framework that reconstructs each autonomous language-model agent’s run in Capture-the-Flag (CTF) challenges into evidence‑grounded solve profiles. By decomposing actions into penetration‑testing phases and techniques, it distinguishes genuine exploitation from shortcut methods such as memorized recall or guessing. Applying the framework to 1,435 CTF attempts by six models on 240 challenges shows that only 62‑87% of recovered flags are trace‑verified, highlighting that many successes rely on shallow trajectories rather than true exploitation.

By Kimberly Milner, Minghao Shao, Nanda Rani, Haoran Xi, Venkata Sai Charan Putrevu, Meet Udeshi, Sandeep K. Shukla, Prashanth Krishnamurthy, Farshad Khorrami, Muhammad Shafique, Ramesh Karri
arXiv Machine Learning
Jul 30

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.

By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov
arXiv AI
Jun 18

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.

By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang
arXiv AI
Jun 2

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.

By Hiskias Dingeto, Will Leeney
Hugging Face Trending Papers
Jul 29

ToxScreen: Detecting Whether an LLM Has Been Poisoned

As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.