REVIEW 20 cited by
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
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
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
read the original abstract
Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabilities simply by optimizing over a next-word prediction objective. With the emergence of their properties and encoded knowledge, the risk of LLMs producing harmful outputs increases, making them unfit for scalable deployment for the public. In this work, we propose a new safety evaluation benchmark RED-EVAL that carries out red-teaming. We show that even widely deployed models are susceptible to the Chain of Utterances-based (CoU) prompting, jailbreaking closed source LLM-based systems such as GPT-4 and ChatGPT to unethically respond to more than 65% and 73% of harmful queries. We also demonstrate the consistency of the RED-EVAL across 8 open-source LLMs in generating harmful responses in more than 86% of the red-teaming attempts. Next, we propose RED-INSTRUCT--An approach for the safety alignment of LLMs. It constitutes two phases: 1) HARMFULQA data collection: Leveraging CoU prompting, we collect a dataset that consists of 1.9K harmful questions covering a wide range of topics, 9.5K safe and 7.3K harmful conversations from ChatGPT; 2) SAFE-ALIGN: We demonstrate how the conversational dataset can be used for the safety alignment of LLMs by minimizing the negative log-likelihood over helpful responses and penalizing over harmful responses by gradient accent over sample loss. Our model STARLING, a fine-tuned Vicuna-7B, is observed to be more safely aligned when evaluated on RED-EVAL and HHH benchmarks while preserving the utility of the baseline models (TruthfulQA, MMLU, and BBH).
Forward citations
Cited by 20 Pith papers
-
Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
Misrouter enables input-only attacks on MoE LLMs by optimizing queries on open-source surrogates to route toward weakly aligned experts and transferring them to public APIs.
-
When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
CREST-Search is a red-teaming framework that crafts seemingly benign search queries to induce unsafe citations from web-augmented LLMs, backed by a new WebSearch-Harm dataset for fine-tuning a specialized attacker model.
-
Evalet: Evaluating Large Language Models through Functional Fragmentation
Evalet applies functional fragmentation to deliver fragment-level qualitative analysis of LLM evaluations, with a user study showing 48% more misalignment detections than holistic scoring.
-
Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
MTK detects jailbreaks by monitoring the evolution of prompt neighborhood structures on the data manifold through LLM layers, reporting 95% TPR at 5% FPR on benign and 2% on pseudo-malicious prompts plus 85% TPR under...
-
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
SafeSteer restricts reverse KL penalty to safety tokens selected via activation steering, achieving strong safety on seven benchmarks with minimal degradation on five capability benchmarks using only 100 harmful sampl...
-
Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South
A participatory red-teaming project in the Global South created the PLACES dataset of 26k T2I failure examples that reveal unique cultural and linguistic harms missed by existing safety frameworks.
-
You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation
NeWTral is a non-linear weight translation framework using MoE routing that reduces average attack success rate from 70% to 13% on unsafe domain adapters across Llama, Mistral, Qwen, and Gemma models up to 72B while r...
-
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
MultiBreak is a large diverse multi-turn jailbreak benchmark that achieves substantially higher attack success rates on LLMs than prior datasets and reveals topic-specific vulnerabilities in multi-turn settings.
-
Diversifying Toxicity Search in Large Language Models Through Speciation
ToxSearch-S applies unsupervised speciation to evolutionary prompt search, maintaining capacity-limited species with exemplar leaders and species-aware selection to achieve higher peak toxicity and broader semantic co...
-
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
Personalization through long-term memory in LLM agents increases harmful query success rates by 15.8-243.7% via intent legitimation, measured on the new PS-Bench benchmark across frameworks.
-
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses
A systemization of LLM jailbreak security that adds linked taxonomies, an evaluation platform, and JailbreakDB, while its main attack–defense comparison results remain deferred.
-
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain
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.
-
Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
Phonetic perturbations fragment safety-critical tokens in LLMs, suppressing attribution scores while preserving input understanding and causing safety mechanisms to fail despite good comprehension.
-
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.
-
ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models
Prompts evolved with small lexical mutations elicit toxic output from aligned LLMs, and these prompts transfer across models with toxicity reduced by roughly 30–54%.
-
Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks
CoopGuard's defer-tempt-analyze-coordinate agents cut reported jailbreak success and raise attacker token costs on the new EMRA benchmark, but the deceptive-rate metric is partly defined by the paper's own scoring rubric.
-
Distributed Quality-Diversity Search for Toxicity in Large Language Models
ToxSearch-S extends evolutionary toxicity search with embedding-driven speciation and MPI distribution, matching baseline peak toxicity while showing lower search pressure and 1.8-3.2x speedups.
-
LLM-Safety Evaluations Lack Robustness
LLM safety evaluations are hindered by noise in dataset curation, automated red-teaming, response generation, and LLM-judge evaluation, making fair comparisons difficult and slowing progress.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
-
Jailbreak Attacks and Defenses Against Large Language Models: A Survey
A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.