Pith Number

pith:YOY6QLV6

pith:2024:YOY6QLV6QQC7SP2TV3OYWEU3HF

not attested not anchored not stored refs resolved

Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Jiaxing Song, Ke Xu, Qi Li, Sibo Yi, Tianshuo Cong, Xinlei He, Yule Liu, Zhen Sun

A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.

arxiv:2407.04295 v2 · 2024-07-05 · cs.CR · cs.AI · cs.CL · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YOY6QLV6QQC7SP2TV3OYWEU3HF}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

we propose a comprehensive and detailed taxonomy of jailbreak attack and defense methods... and present a coherent diagram illustrating their relationships. We also conduct an investigation into the current evaluation methods and compare them from different perspectives.

C2weakest assumption

That the proposed taxonomy and sub-classifications accurately and comprehensively capture the current landscape of attacks and defenses without significant omissions or overlaps that would require revision.

C3one line summary

A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.

References

126 extracted · 126 resolved · 21 Pith anchors

[1] Detecting Language Model Attacks with Perplexity 2023 · arXiv:2308.14132

[2] Jailbreaking leading safety-aligned LLMs with simple adaptive attacks 2024

[3] Gemini: A Family of Highly Capable Multimodal Models 2023 · arXiv:2312.11805

[4] Introducing claude

[5] Many-shot jailbreaking 2024

Formal links

1 machine-checked theorem link

Cited by

37 papers in Pith

Understanding Goal Generalisation in Sequential Reinforcement Learning

AI Security Research Should Better Incentivize Defense Research

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

Receipt and verification

First computed	2026-05-17T23:38:53.831024Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c3b1e82ebe8405f93f53aedd8b129b39727bf5386f751e950e9ed0805c9ddf38

Aliases

arxiv: 2407.04295 · arxiv_version: 2407.04295v2 · doi: 10.48550/arxiv.2407.04295 · pith_short_12: YOY6QLV6QQC7 · pith_short_16: YOY6QLV6QQC7SP2T · pith_short_8: YOY6QLV6

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/YOY6QLV6QQC7SP2TV3OYWEU3HF \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: c3b1e82ebe8405f93f53aedd8b129b39727bf5386f751e950e9ed0805c9ddf38

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "badbb006037acd708228bc413519371479731de0270eb8b97df398aeee46af08",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2024-07-05T06:57:30Z",
    "title_canon_sha256": "f74598f44eea1fd513b7b56c50447230bcf80aef8f4a84aca6c92583188144f7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2407.04295",
    "kind": "arxiv",
    "version": 2
  }
}