Pith. sign in

REVIEW 8 cited by

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.00061 v2 pith:IW7J2RLI submitted 2025-02-27 cs.CR cs.LG

classification cs.CRcs.LG
keywords attacksdefensesadaptiveagentsattackexternalindirectinjection
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt injection (IPI) attacks. Despite defenses designed for IPI attacks, their robustness remains questionable due to insufficient testing against adaptive attacks. In this paper, we evaluate eight different defenses and bypass all of them using adaptive attacks, consistently achieving an attack success rate of over 50%. This reveals critical vulnerabilities in current defenses. Our research underscores the need for adaptive attack evaluation when designing defenses to ensure robustness and reliability. The code is available at https://github.com/uiuc-kang-lab/AdaptiveAttackAgent.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments

    cs.CR 2026-07 conditional novelty 7.0 of 10

    Adaptive adversarial source-code comments evade four LLM vulnerability detectors at >90% success on 125 real null-pointer bugs without altering program behavior.

  2. Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection

    cs.CR 2026-04 unverdicted novelty 7.0 of 10

    The work introduces and partially evaluates seven cross-domain prompt injection detectors, reporting F1 gains on benchmarks like deepset/prompt-injections and indirect-injection sets via local alignment, stylometry, a...

  3. Prompt Injection as Role Confusion

    cs.CL 2026-02 unverdicted novelty 7.0 of 10

    Prompt injection works because models internally treat text that sounds like a trusted role as if it were tagged as that role, and this confusion can be measured before generation.

  4. Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment

    cs.CR 2025-09 conditional novelty 5.0 of 10

    Attacker-controlled tool descriptions and return values can hijack tool invocation in popular LLM coding agents, yielding remote code execution and denial of service.

  5. Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree

    cs.CR 2025-07 conditional novelty 5.0 of 10

    GCG-optimized trigger strings embedded in HTML can command LLM web agents to perform attacker-chosen actions, including credential exfiltration.

  6. VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models

    cs.CV 2025-06 reject novelty 5.0 of 10

    VSF-Med introduces an eight-dimension, judge-scored vulnerability score for medical VLMs and reports that all five tested models are most vulnerable to persistent attack effects, with Llama-3.2 showing the largest drop.

  7. EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks

    cs.AI 2025-05 reject novelty 5.0 of 10

    EVA evolves environmental injection payloads through a keyword-utility loop, achieving up to 80% attack success in the body's pop-up tests, while the abstract's stronger claims are not supported by the reported experiments.

  8. Evaluation and Benchmarking of LLM Agents: A Survey

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A review that proposes a two-dimensional taxonomy for evaluating LLM agents and highlights enterprise-specific evaluation gaps.

Pith tools