WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

• URL: http://arxiv.org/abs/2406.18495v2
• Date: Tue, 9 Jul 2024 05:06:49 GMT
• Title: WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
• Authors: Seungju Han, Kavel Rao, Allyson Ettinger, Liwei Jiang, Bill Yuchen Lin, Nathan Lambert, Yejin Choi, Nouha Dziri,
• Abstract summary: We introduce WildGuard -- an open, light-weight moderation tool for LLM safety. WildGuard achieves three goals: identifying malicious intent in user prompts, detecting safety risks of model responses, and determining model refusal rate.
• Score: 54.10865585773691
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal rate. Together, WildGuard serves the increasing needs for automatic safety moderation and evaluation of LLM interactions, providing a one-stop tool with enhanced accuracy and broad coverage across 13 risk categories. While existing open moderation tools such as Llama-Guard2 score reasonably well in classifying straightforward model interactions, they lag far behind a prompted GPT-4, especially in identifying adversarial jailbreaks and in evaluating models' refusals, a key measure for evaluating safety behaviors in model responses. To address these challenges, we construct WildGuardMix, a large-scale and carefully balanced multi-task safety moderation dataset with 92K labeled examples that cover vanilla (direct) prompts and adversarial jailbreaks, paired with various refusal and compliance responses. WildGuardMix is a combination of WildGuardTrain, the training data of WildGuard, and WildGuardTest, a high-quality human-annotated moderation test set with 5K labeled items covering broad risk scenarios. Through extensive evaluations on WildGuardTest and ten existing public benchmarks, we show that WildGuard establishes state-of-the-art performance in open-source safety moderation across all the three tasks compared to ten strong existing open-source moderation models (e.g., up to 26.4% improvement on refusal detection). Importantly, WildGuard matches and sometimes exceeds GPT-4 performance (e.g., up to 3.9% improvement on prompt harmfulness identification). WildGuard serves as a highly effective safety moderator in an LLM interface, reducing the success rate of jailbreak attacks from 79.8% to 2.4%.

Related papers

• Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring [47.40698758003993]
  We propose an improved transfer attack method that guides malicious prompt construction by locally training a mirror model of the target black-box model through benign data distillation. Our approach achieved a maximum attack success rate of 92%, or a balanced value of 80% with an average of 1.5 detectable jailbreak queries per sample against GPT-3.5 Turbo.
  arXiv  Detail & Related papers  (2024-10-28T14:48:05Z)
• PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing [1.474945380093949]
  Inference-Time Guardrails (ITG) offer solutions that shift model output distributions towards compliance. Current methods struggle in balancing safety with helpfulness. We propose PrimeGuard, a novel ITG method that utilizes structured control flow.
  arXiv  Detail & Related papers  (2024-07-23T09:14:27Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models [66.34505141027624]
  We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics. WildTeaming reveals previously unidentified vulnerabilities of frontier LLMs, resulting in up to 4.6x more diverse and successful adversarial attacks.
  arXiv  Detail & Related papers  (2024-06-26T17:31:22Z)
• SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance [48.80398992974831]
  SafeAligner is a methodology implemented at the decoding stage to fortify defenses against jailbreak attacks. We develop two specialized models: the Sentinel Model, which is trained to foster safety, and the Intruder Model, designed to generate riskier responses. We show that SafeAligner can increase the likelihood of beneficial tokens, while reducing the occurrence of harmful ones.
  arXiv  Detail & Related papers  (2024-06-26T07:15:44Z)
• Jailbreaking as a Reward Misspecification Problem [80.52431374743998]
  We propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process. We introduce a metric ReGap to quantify the extent of reward misspecification and demonstrate its effectiveness. We present ReMiss, a system for automated red teaming that generates adversarial prompts in a reward-misspecified space.
  arXiv  Detail & Related papers  (2024-06-20T15:12:27Z)
• JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks [34.95274579737075]
  We propose JailGuard, a universal detection framework for jailbreaking and hijacking attacks across LLMs and MLLMs. JailGuard operates on the principle that attacks are inherently less robust than benign ones, regardless of method or modality. We build the first comprehensive multi-modal attack dataset, containing 11,000 data items across 15 known attack types.
  arXiv  Detail & Related papers  (2023-12-17T17:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.