Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

• URL: http://arxiv.org/abs/2407.15549v2
• Date: Wed, 21 Aug 2024 23:22:40 GMT
• Title: Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
• Authors: Abhay Sheshadri, Aidan Ewart, Phillip Guo, Aengus Lynch, Cindy Wu, Vivek Hebbar, Henry Sleight, Asa Cooper Stickland, Ethan Perez, Dylan Hadfield-Menell, Stephen Casper,
• Abstract summary: Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. Recent work on red-teaming, model editing, and interpretability suggests that this challenge stems from how (adversarial) fine-tuning largely serves to suppress rather than remove undesirable capabilities.
• Score: 13.03032975937872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful text from models that were fine-tuned to be harmless. Recent work on red-teaming, model editing, and interpretability suggests that this challenge stems from how (adversarial) fine-tuning largely serves to suppress rather than remove undesirable capabilities from LLMs. Prior work has introduced latent adversarial training (LAT) as a way to improve robustness to broad classes of failures. These prior works have considered untargeted latent space attacks where the adversary perturbs latent activations to maximize loss on examples of desirable behavior. Untargeted LAT can provide a generic type of robustness but does not leverage information about specific failure modes. Here, we experiment with targeted LAT where the adversary seeks to minimize loss on a specific competing task. We find that it can augment a wide variety of state-of-the-art methods. First, we use targeted LAT to improve robustness to jailbreaks, outperforming a strong R2D2 baseline with orders of magnitude less compute. Second, we use it to more effectively remove backdoors with no knowledge of the trigger. Finally, we use it to more effectively unlearn knowledge for specific undesirable tasks in a way that is also more robust to re-learning. Overall, our results suggest that targeted LAT can be an effective tool for defending against harmful behaviors from LLMs.

Related papers

• DROJ: A Prompt-Driven Attack against Large Language Models [0.0]
  Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Despite massive alignment efforts, LLMs remain susceptible to adversarial jailbreak attacks. We introduce a novel approach, Directed Rrepresentation Optimization Jailbreak (DROJ)
  arXiv  Detail & Related papers  (2024-11-14T01:48:08Z)
• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
  We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
  arXiv  Detail & Related papers  (2024-08-20T09:36:04Z)
• Defending Against Unforeseen Failure Modes with Latent Adversarial Training [7.141982906162117]
  Red-teaming and adversarial training (AT) are commonly used to improve robustness. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without leveraging knowledge of what they are. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness to novel attacks and performance on clean data relative to AT.
  arXiv  Detail & Related papers  (2024-03-08T04:22:48Z)
• Coercing LLMs to do and reveal (almost) anything [80.8601180293558]
  It has been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. We argue that the spectrum of adversarial attacks on LLMs is much larger than merely jailbreaking.
  arXiv  Detail & Related papers  (2024-02-21T18:59:13Z)
• Machine Unlearning in Large Language Models [8.14992136443131]
  This paper introduces a novel machine unlearning framework into large language models. Our objectives are to make LLMs not produce harmful, hallucinatory, or privacy-compromising responses. Experimental results show that our approach effectively meets unlearning objectives without substantially compromising model performance.
  arXiv  Detail & Related papers  (2024-02-03T05:14:56Z)
• The Philosopher's Stone: Trojaning Plugins of Large Language Models [22.67696768099352]
  Open-source Large Language Models (LLMs) have recently gained popularity because of their comparable performance to proprietary LLMs. To efficiently fulfill domain-specialized tasks, open-source LLMs can be refined, without expensive accelerators, using low-rank adapters. It is still unknown whether low-rank adapters can be exploited to control LLMs.
  arXiv  Detail & Related papers  (2023-12-01T06:36:17Z)
• Making Harmful Behaviors Unlearnable for Large Language Models [50.44915524846857]
  Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. LLMs can be easily fine-tuned into harmful assistants as the fine-tuning data often contains implicit or explicit harmful content. This paper proposes a controllable training framework that makes harmful behaviors unlearnable during the fine-tuning process.
  arXiv  Detail & Related papers  (2023-11-02T09:18:21Z)
• Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis [127.85293480405082]
  The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. Existing alignment methods usually direct LLMs toward the favorable outcomes by utilizing human-annotated, flawless instruction-response pairs. This study proposes a novel alignment technique based on mistake analysis, which deliberately exposes LLMs to erroneous content to learn the reasons for mistakes and how to avoid them.
  arXiv  Detail & Related papers  (2023-10-16T14:59:10Z)
• Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks [67.86285142381644]
  Recent advances in instruction-following large language models amplify the dual-use risks for malicious purposes. Dual-use is difficult to prevent as instruction-following capabilities now enable standard attacks from computer security. We show that instruction-following LLMs can produce targeted malicious content, including hate speech and scams.
  arXiv  Detail & Related papers  (2023-02-11T15:57:44Z)
• Effective Targeted Attacks for Adversarial Self-Supervised Learning [58.14233572578723]
  unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. We propose a novel positive mining for targeted adversarial attack to generate effective adversaries for adversarial SSL frameworks. Our method demonstrates significant enhancements in robustness when applied to non-contrastive SSL frameworks, and less but consistent robustness improvements with contrastive SSL frameworks.
  arXiv  Detail & Related papers  (2022-10-19T11:43:39Z)
• RelaxLoss: Defending Membership Inference Attacks without Losing Utility [68.48117818874155]
  We propose a novel training framework based on a relaxed loss with a more achievable learning target. RelaxLoss is applicable to any classification model with added benefits of easy implementation and negligible overhead. Our approach consistently outperforms state-of-the-art defense mechanisms in terms of resilience against MIAs.
  arXiv  Detail & Related papers  (2022-07-12T19:34:47Z)

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.