Pith. sign in

REVIEW 10 cited by

Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

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 2402.09283 v3 pith:FERCOTQI submitted 2024-02-14 cs.CL cs.AIcs.CYcs.LG

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

Large Language Models (LLMs) are now commonplace in conversation applications. However, their risks of misuse for generating harmful responses have raised serious societal concerns and spurred recent research on LLM conversation safety. Therefore, in this survey, we provide a comprehensive overview of recent studies, covering three critical aspects of LLM conversation safety: attacks, defenses, and evaluations. Our goal is to provide a structured summary that enhances understanding of LLM conversation safety and encourages further investigation into this important subject. For easy reference, we have categorized all the studies mentioned in this survey according to our taxonomy, available at: https://github.com/niconi19/LLM-conversation-safety.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis

    cs.CL 2026-03 conditional novelty 7.0 of 10

    Seven clinician-informed safety criteria enable LLM-as-a-Judge to reach substantial agreement with human consensus (Cohen's κ up to 0.75) on evaluating LLM responses to users demonstrating psychosis.

  2. YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models

    cs.HC 2025-09 conditional novelty 6.0 of 10

    Introduces YAIR, a youth-GenAI risk benchmark, and YouthSafe, a fine-tuned classifier with AUPRC 0.94 on it, though it compares a trained model to untrained baselines.

  3. Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders

    cs.CR 2026-05 unverdicted novelty 5.0 of 10

    Graph-context LLM fraud defenders improve early refusal under replay and adaptive multi-round attacks compared to text baselines but increase benign over-refusal, with the cost localized to how the LLM consumes struct...

  4. REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Reflector trains LLMs to internalize step-wise self-reflection through SFT on teacher data followed by RL with outcome and validity rewards, reporting over 90% defense success against indirect jailbreaks and a 5.85% g...

  5. REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Reflector internalizes step-wise self-reflection in LLMs via teacher-guided SFT then RL with outcome and validity rewards, claiming over 90% defense success against indirect jailbreaks plus utility gains like 5.85% on GSM8K.

  6. MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security

    cs.CL 2025-09 conditional novelty 5.0 of 10

    MoGUv2 embeds small routers in the deeper layers of LLMs to dynamically blend a helpful variant and a refusal variant, improving safety against jailbreak and fine-tuning attacks while preserving usability.

  7. 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.

  8. An Empirical Study of Vulnerable Package Dependencies in LLM Repositories

    cs.CR 2025-08 conditional novelty 4.0 of 10

    In 52 open-source LLM projects, 75.8% of those with dependency configs use at least one vulnerable package, and half of supply chain vulnerabilities stay undisclosed for over 56 months.

  9. A Survey on the Memory Mechanism of Large Language Model based Agents

    cs.AI 2024-04 accept novelty 3.0 of 10

    A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.

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

    cs.CR 2024-09 unverdicted novelty 2.0 of 10

    Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.

Pith tools