Pith. sign in

REVIEW 6 cited by

Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks

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 2403.03792 v2 pith:7FXSHDWD submitted 2024-03-06 cs.CR cs.LG

Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks

classification cs.CR cs.LG
keywords triggersattacksneuralexecexecutiongeneratehandcraftedinjection
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of execution triggers as a differentiable search problem and use learning-based methods to autonomously generate them. Our results demonstrate that a motivated adversary can forge triggers that are not only drastically more effective than current handcrafted ones but also exhibit inherent flexibility in shape, properties, and functionality. In this direction, we show that an attacker can design and generate Neural Execs capable of persisting through multi-stage preprocessing pipelines, such as in the case of Retrieval-Augmented Generation (RAG)-based applications. More critically, our findings show that attackers can produce triggers that deviate markedly in form and shape from any known attack, sidestepping existing blacklist-based detection and sanitation approaches.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

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

  1. AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

    cs.CR 2024-06 unverdicted novelty 8.0

    AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.

  2. Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

    cs.IR 2024-09 unverdicted novelty 7.0

    Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gap...

  3. Evaluation of Prompt Injection Defenses in Large Language Models

    cs.CR 2026-04 unverdicted novelty 6.0

    Output filtering implemented in application code is the only defense that survived an adaptive prompt-injection attacker across 15,000 attacks; model-based defenses all broke.

  4. ACE: A Security Architecture for LLM-Integrated App Systems

    cs.CR 2025-04 unverdicted novelty 6.0

    ACE decouples planning into abstract and concrete phases with static information-flow verification and enforces execution barriers to secure LLM app systems against prompt injection and related attacks.

  5. Evaluation of Prompt Injection Defenses in Large Language Models

    cs.CR 2026-04 unverdicted novelty 5.0

    Only output filtering with hardcoded rules in application code prevented prompt injection leaks in LLMs, as all model-based defenses were defeated by an adaptive attacker.

  6. Assessing Automated Prompt Injection Attacks in Agentic Environments

    cs.CR 2026-06 unverdicted novelty 4.0

    Black-box optimization outperforms gradient-based methods for prompt injection on LLM agents, with success depending on attacker model strength and limited transfer from small to frontier models.