Pith. sign in

REVIEW 20 cited by

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

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 2402.16717 v1 pith:SAGV6OD3 submitted 2024-02-26 cs.CL cs.AIcs.CR

classification cs.CLcs.AIcs.CR
keywords encryptionllmspersonalizedcodechameleonframeworkgenerationhypothesisintent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful attacks, introducing a hypothesis for the safety mechanism of aligned LLMs: intent security recognition followed by response generation. Grounded in this hypothesis, we propose CodeChameleon, a novel jailbreak framework based on personalized encryption tactics. To elude the intent security recognition phase, we reformulate tasks into a code completion format, enabling users to encrypt queries using personalized encryption functions. To guarantee response generation functionality, we embed a decryption function within the instructions, which allows the LLM to decrypt and execute the encrypted queries successfully. We conduct extensive experiments on 7 LLMs, achieving state-of-the-art average Attack Success Rate (ASR). Remarkably, our method achieves an 86.6\% ASR on GPT-4-1106.

Discussion (0). Sign in to comment.

Forward citations

Cited by 20 Pith papers

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

  1. Do LLMs Know Their Vulnerable Scenarios?

    cs.AI 2026-07 conditional novelty 7.0 of 10

    Scenario jailbreaks suppress refusal via internal concept directions; Concept2Scenario attributes those concepts with SAEs and turns them into transferable natural-language attack scenarios.

  2. Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion

    cs.CR 2026-04 unverdicted novelty 7.0 of 10

    HMNS is a new jailbreak method that uses causal head identification and nullspace-constrained injection to achieve higher attack success rates than prior techniques on aligned language models.

  3. RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation

    cs.CR 2026-07 conditional novelty 6.0 of 10

    RoguePrompt, a Vigenère+ROT13 self-reconstruction jailbreak, achieves 70.18% execution@3 and 93.93% bypass@3 across GPT-4o, Claude 3 Opus, and Gemini 1.5 Pro on 313 StrongREJECT prompts.

  4. MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Turn-level group-relative credit assignment (immediate plus future return) trains multi-turn jailbreak attackers that reach about 98% ASR5@3, beating prior multi-turn methods by roughly 11 points.

  5. SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling

    cs.CR 2026-06 unverdicted novelty 6.0 of 10

    SafeSpec integrates a latent safety head into speculative LLM decoding with rollback and reflective multi-sampling, cutting attack success rates 15% on Qwen3-32B while retaining 2.06x speedup on normal workloads.

  6. Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines

    cs.AI 2026-06 conditional novelty 6.0 of 10

    Disguising unsafe operations as routine software-engineering tests makes coding agents execute them at high verified rates, revealing a gap between language-layer refusal and execution-layer harm.

  7. RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry

    cs.CR 2026-05 unverdicted novelty 6.0 of 10

    RouteScan identifies malicious prompts in MoE LLMs using GPU expert routing telemetry as a privacy-preserving fingerprint, achieving AUROC above 0.93 on unseen harmful domains.

  8. Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation

    cs.CR 2026-04 unverdicted novelty 6.0 of 10

    Automation-Exploit is a multi-agent LLM system that uses conditional digital-twin validation to perform risk-mitigated exploitation of logical, web, and memory-corruption vulnerabilities in black-box targets.

  9. Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models

    cs.CR 2026-04 conditional novelty 6.0 of 10

    A new benchmark exposes food-safety gaps in current LLMs and guardrails, and a fine-tuned 4B model is offered as a domain-specific fix.

  10. 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.

  11. Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain

    cs.CL 2025-09 unverdicted novelty 6.0 of 10

    CoRT achieves 95% average attack success rate on nine LLMs by using iterative risk-concealing prompts and a controller that scores concealment levels on a new 522-instruction financial risk benchmark.

  12. ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

    cs.CR 2025-08 conditional novelty 6.0 of 10

    ASTRA is an automated red-teaming agent that uses knowledge-graph-guided spatial and temporal probing to find 11-66% more safety violations in AI coding assistants than existing tools.

  13. PUZZLED: Jailbreaking LLMs through Word-Based Puzzles

    cs.AI 2025-08 unverdicted novelty 6.0 of 10

    PUZZLED masks harmful keywords as word-search, anagram, or crossword puzzles and achieves a reported 88.8% average attack success rate across five leading LLMs.

  14. SALLIE: Safeguarding Against Latent Language & Image Exploits

    cs.CR 2026-04 unverdicted novelty 5.0 of 10

    SALLIE detects jailbreaks in text and vision-language models by extracting residual stream activations, scoring maliciousness per layer with k-NN, and ensembling predictions, outperforming baselines on multiple datasets.

  15. ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs

    cs.CR 2025-11 unverdicted novelty 5.0 of 10

    ASTRA is an automated closed-loop framework that discovers, retrieves, and evolves jailbreak attack strategies for LLMs using a dynamic three-tier strategy library and outperforms baselines in black-box settings.

  16. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

    cs.CL 2025-08 reject novelty 5.0 of 10

    Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.

  17. Towards terahertz nanomechanics

    physics.app-ph 2025-08 unverdicted novelty 5.0 of 10

    Suspended Lamb-wave resonators in lithium niobate films thinned from 300 nm to 67 nm reach 220 GHz, doubling the prior record.

  18. Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning

    cs.AI 2025-08 unverdicted novelty 5.0 of 10

    A jailbreak defense that reasons about hidden manipulations in attack prompts, trained with supervised fine-tuning plus entropy-guided reinforcement learning, generalizes to attacks never seen in training.

  19. Jailbreak Attacks and Defenses Against Large Language Models: A Survey

    cs.CR 2024-07 accept novelty 4.0 of 10

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

  20. Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

    cs.CR 2025-02 unverdicted novelty 2.0 of 10

    A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.

Pith tools