Pith. sign in

REVIEW 18 cited by

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

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 2402.14872 v2 pith:JJBQJMR2 submitted 2024-02-21 cs.CL cs.AIcs.NE

classification cs.CLcs.AIcs.NE
keywords jailbreakpromptssemanticllmsmetricspromptdefensedefenses
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs. Most jailbreak prompt methods use a combination of jailbreak templates followed by questions to ask to create jailbreak prompts. However, existing jailbreak prompt designs generally suffer from excessive semantic differences, resulting in an inability to resist defenses that use simple semantic metrics as thresholds. Jailbreak prompts are semantically more varied than the original questions used for queries. In this paper, we introduce a Semantic Mirror Jailbreak (SMJ) approach that bypasses LLMs by generating jailbreak prompts that are semantically similar to the original question. We model the search for jailbreak prompts that satisfy both semantic similarity and jailbreak validity as a multi-objective optimization problem and employ a standardized set of genetic algorithms for generating eligible prompts. Compared to the baseline AutoDAN-GA, SMJ achieves attack success rates (ASR) that are at most 35.4% higher without ONION defense and 85.2% higher with ONION defense. SMJ's better performance in all three semantic meaningfulness metrics of Jailbreak Prompt, Similarity, and Outlier, also means that SMJ is resistant to defenses that use those metrics as thresholds.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

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

  1. MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?

    cs.CL 2025-07 conditional novelty 7.0 of 10

    MOCHA is a benchmark of 10.5K malicious coding prompts, including multi-turn decomposition attacks, showing code LLMs reject these incremental attacks at much lower rates and that fine-tuning on the benchmark improves...

  2. SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense

    cs.CV 2026-08 conditional novelty 6.0 of 10

    SafeCA reduces text-to-video jailbreak success by roughly 20% relative to T2VShield by masking anomalous cross-attention activations using clean-prompt statistics.

  3. Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Evolved self-propagating prompt payloads spread between LLM agents in two simulated settings, with harmful payloads less transmissible and a system-prompt warning conferring near-total immunity.

  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. SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A history-aware guard model with an LLM judge is reported to cut jailbreak success on mobile agent tasks from 86.1% to 8.4% while keeping task completion unchanged at 77.8%.

  6. SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

    cs.CR 2025-06 conditional novelty 6.0 of 10

    A security-aware prompt compressor that reveals the hidden intent of jailbreak prompts and injects it into the system prompt reduces average attack success from 35% to 1% with negligible overhead.

  7. T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

    cs.CV 2025-05 conditional novelty 6.0 of 10

    An LLM-driven discrete optimization with prompt mutation can rewrite unsafe prompts to bypass text-to-video safety filters and produce harmful videos with higher success than existing methods.

  8. When Testing AI Tests Us: Safeguarding Mental Health on the Digital Frontlines

    cs.CY 2025-04 conditional novelty 6.0 of 10

    AI red-teaming can harm the mental health of the people who do it, and protective practices from four comparable professions can be adapted to support them.

  9. CogMorph: Cognitive Morphing Attacks for Text-to-Image Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    CogMorph escalates the toxicity of text-to-image outputs by contextually rewriting prompts with retrieved harmful features, claiming higher emotional harm than prior jailbreak attacks.

  10. Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Environmental illusions cause 5-7% accuracy drops in lane detection models and can trigger collisions in closed-loop simulation, with a proposed defense (MIDA) recovering ~4% robustness.

  11. 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.

  12. VERA: Variational Inference Framework for Jailbreaking Large Language Models

    cs.CR 2025-06 conditional novelty 5.0 of 10

    VERA frames black-box jailbreaking as variational inference, training a LoRA-tuned attacker that samples diverse fluent prompts; reported ASRs are high but several evaluation choices weaken the SOTA claims.

  13. One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs

    cs.CR 2025-05 conditional novelty 5.0 of 10

    ArrAttack fine-tunes a judge on the SmoothLLM defense, uses it to filter rewriting-attack data, and trains a generator that produces jailbreak prompts transferring across defenses.

  14. Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A stacked-cipher jailbreak with adaptive code selection achieves 80.8% to 100% attack success on commercial large reasoning models.

  15. T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models

    cs.CR 2025-04 conditional novelty 5.0 of 10

    T2VShield combines LLM-based prompt rewriting with multi-scale video risk detection and reports large reductions in jailbreak success across five text-to-video platforms.

  16. KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

    cs.CR 2025-02 conditional novelty 5.0 of 10

    A distilled open-source attacker, KDA, imitates three jailbreak methods to write diverse attack prompts, and reports higher success and efficiency than each teacher.

  17. LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

    cs.CR 2024-12 conditional novelty 5.0 of 10

    LLM-Virus uses an evolutionary algorithm with an LLM as crossover, mutation, and fitness operator to evolve jailbreak templates, reporting state-of-the-art attack success on HarmBench and AdvBench.

  18. SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models

    cs.CR 2025-06 conditional novelty 4.0 of 10

    Across 510 HarmBench behaviors and seven attack methods, GPT-4 models show more consistent jailbreak resilience than DeepSeek models, whose vulnerability grows with scale.

Pith tools