Pith. sign in

REVIEW 11 cited by

Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

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 2305.14965 v4 pith:OOL2AAXT submitted 2023-05-24 cs.CL

classification cs.CL
keywords jailbreakllmsattackscommercialeffectivenessfurtherjailbreaksknown
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive outputs, and violations of content regulator policies. Limited studies have been conducted to formalize and analyze these attacks and their mitigations. We bridge this gap by proposing a formalism and a taxonomy of known (and possible) jailbreaks. We survey existing jailbreak methods and their effectiveness on open-source and commercial LLMs (such as GPT-based models, OPT, BLOOM, and FLAN-T5-XXL). We further discuss the challenges of jailbreak detection in terms of their effectiveness against known attacks. For further analysis, we release a dataset of model outputs across 3700 jailbreak prompts over 4 tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

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

  1. Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface

    cs.CR 2025-01 conditional novelty 7.0 of 10

    Attackers can use the loss signal from a remote LLM fine-tuning API to optimize adversarial prefix and suffix tokens, turning existing prompt injections into high-success attacks on closed-weight Gemini models.

  2. AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models

    cs.CR 2026-04 conditional novelty 6.0 of 10

    Obfuscation alone reaches 76% success against intent-aware defenses; pairing it with emotional manipulation yields 97.6% success under a modeled composite evaluation of 250 prompts.

  3. Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels

    cs.CR 2025-10 conditional novelty 6.0 of 10

    Indirect prompt injection through ads, webviews, and notifications reliably diverts mobile LLM agents into leaking data and installing malware across eight evaluated agents.

  4. SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

    cs.CR 2025-10 conditional novelty 6.0 of 10

    A systemization of LLM jailbreak security that adds linked taxonomies, an evaluation platform, and JailbreakDB, while its main attack–defense comparison results remain deferred.

  5. JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

    cs.CR 2025-08 conditional novelty 6.0 of 10

    JADES judges jailbreak success by decomposing harmful prompts into weighted sub-questions and scoring each part, claiming 98.5% human agreement and showing prior attack success rates are inflated.

  6. Agents Are All You Need for LLM Unlearning

    cs.AI 2025-02 reject novelty 6.0 of 10

    A four-agent pipeline, Vanilla, AuditErase, Critic, and Composer, filters target references out of LLM responses, claiming robust and scalable inference-time unlearning without weight updates.

  7. On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

    cs.CR 2026-08 conditional novelty 5.0 of 10

    A PRISMA-based survey of 85 papers shows agentic LLM security research is attack-heavy and perception-focused, leaving action-layer and code-execution risks understudied.

  8. PromptShield: Deployable Detection for Prompt Injection Attacks

    cs.CR 2025-01 conditional novelty 5.0 of 10

    PromptShield reports a 65.3% true positive rate at 0.1% false positive rate for prompt injection detection, more than six times the best prior model, on its own out-of-distribution evaluation split.

  9. Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration

    cs.CR 2025-05 conditional novelty 4.0 of 10

    Injecting a fine-tuned BERT classifier's category label into LLM prompts improves accuracy on a 150-question automotive jailbreak benchmark, but the evaluation is self-referential and lacks external validation.

  10. Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs

    cs.CL 2025-09 conditional novelty 3.0 of 10

    A survey categorizing prompt-based attacks on LLMs into four classes and proposing aspirational goals of un-distillable, un-finetunable, and un-editable models.

  11. SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

    cs.CR 2025-06 conditional novelty 3.0 of 10

    A systematization-of-knowledge survey that categorizes LLM privacy risks into training data, prompts, outputs, and agents, and reviews limitations of current mitigations.

Pith tools