Tamper-Resistant Safeguards for Open-Weight LLMs

• URL: http://arxiv.org/abs/2408.00761v3
• Date: Sat, 14 Sep 2024 02:43:00 GMT
• Title: Tamper-Resistant Safeguards for Open-Weight LLMs
• Authors: Rishub Tamirisa, Bhrugu Bharathi, Long Phan, Andy Zhou, Alice Gatti, Tarun Suresh, Maxwell Lin, Justin Wang, Rowan Wang, Ron Arel, Andy Zou, Dawn Song, Bo Li, Dan Hendrycks, Mantas Mazeika,
• Abstract summary: We develop a method for building tamper-resistant safeguards into open-weight LLMs. We find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that tamper-resistance is a tractable problem.
• Score: 57.90526233549399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after thousands of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that tamper-resistance is a tractable problem, opening up a promising new avenue to improve the safety and security of open-weight LLMs.

Related papers

• Global Challenge for Safe and Secure LLMs Track 1 [57.08717321907755]
  The Global Challenge for Safe and Secure Large Language Models (LLMs) is a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) to foster the development of advanced defense mechanisms against automated jailbreaking attacks.
  arXiv  Detail & Related papers  (2024-11-21T08:20:31Z)
• Diversity Helps Jailbreak Large Language Models [16.34618038553998]
  We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context. By simply instructing the LLM to deviate and obfuscate previous attacks, our method dramatically outperforms existing approaches. This revelation exposes a critical flaw in current LLM safety training, suggesting that existing methods may merely mask vulnerabilities rather than eliminate them.
  arXiv  Detail & Related papers  (2024-11-06T19:39:48Z)
• Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models [8.024771725860127]
  Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. We introduce a novel scalable jailbreak attack that preempts the activation of an LLM's safety policies by occupying its computational resources.
  arXiv  Detail & Related papers  (2024-10-05T15:10:01Z)
• Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models [8.024771725860127]
  Jailbreak attacks manipulate large language models into generating harmful content. Jailbreak Antidote enables real-time adjustment of safety preferences by manipulating a sparse subset of the model's internal states. Our analysis reveals that safety-related information in LLMs is sparsely distributed.
  arXiv  Detail & Related papers  (2024-10-03T08:34:17Z)
• CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration [90.36429361299807]
  multimodal large language models (MLLMs) have demonstrated remarkable success in engaging in conversations involving visual inputs. The integration of visual modality has introduced a unique vulnerability: the MLLM becomes susceptible to malicious visual inputs. We introduce a technique termed CoCA, which amplifies the safety-awareness of the MLLM by calibrating its output distribution.
  arXiv  Detail & Related papers  (2024-09-17T17:14:41Z)
• Purple-teaming LLMs with Adversarial Defender Training [57.535241000787416]
  We present Purple-teaming LLMs with Adversarial Defender training (PAD) PAD is a pipeline designed to safeguard LLMs by novelly incorporating the red-teaming (attack) and blue-teaming (safety training) techniques. PAD significantly outperforms existing baselines in both finding effective attacks and establishing a robust safe guardrail.
  arXiv  Detail & Related papers  (2024-07-01T23:25:30Z)
• SLM as Guardian: Pioneering AI Safety with Small Language Models [6.799423428734095]
  Internalizing safeguard features into larger models brought challenges of higher training cost and unintended degradation of helpfulness. In this paper, we leverage a smaller LLM for both harmful query detection and safeguard response generation. We demonstrate the effectiveness of our approach, providing on par or surpassing harmful query detection and safeguard response performance compared to the publicly available LLMs.
  arXiv  Detail & Related papers  (2024-05-30T08:03:15Z)
• Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation [98.02846901473697]
  We propose ECSO (Eyes Closed, Safety On), a training-free protecting approach that exploits the inherent safety awareness of MLLMs. ECSO generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of pre-aligned LLMs.
  arXiv  Detail & Related papers  (2024-03-14T17:03:04Z)
• Rethinking Jailbreaking through the Lens of Representation Engineering [45.70565305714579]
  The recent surge in jailbreaking methods has revealed the vulnerability of Large Language Models (LLMs) to malicious inputs. This study investigates the vulnerability of safety-aligned LLMs by uncovering specific activity patterns.
  arXiv  Detail & Related papers  (2024-01-12T00:50:04Z)
• 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)

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.