The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models

• URL: http://arxiv.org/abs/2502.01225v1
• Date: Mon, 03 Feb 2025 10:28:26 GMT
• Title: The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models
• Authors: Zhiyuan Xu, Joseph Gardiner, Sana Belguith,
• Abstract summary: Fine-tuning attacks can exploit large language models to reveal potentially harmful behaviours. This paper investigates the performance of the Chain of Thought based reasoning model, DeepSeek, when subjected to fine-tuning attacks. We aim to shed light on the vulnerability of Chain of Thought enabled models to fine-tuning attacks and the implications for their safety and ethical deployment.
• Score: 10.524960491460945
• License:
• Abstract: Large language models are typically trained on vast amounts of data during the pre-training phase, which may include some potentially harmful information. Fine-tuning attacks can exploit this by prompting the model to reveal such behaviours, leading to the generation of harmful content. In this paper, we focus on investigating the performance of the Chain of Thought based reasoning model, DeepSeek, when subjected to fine-tuning attacks. Specifically, we explore how fine-tuning manipulates the model's output, exacerbating the harmfulness of its responses while examining the interaction between the Chain of Thought reasoning and adversarial inputs. Through this study, we aim to shed light on the vulnerability of Chain of Thought enabled models to fine-tuning attacks and the implications for their safety and ethical deployment.

Related papers

• Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions [51.51850981481236]
  We introduce POATE, a novel jailbreak technique that harnesses contrastive reasoning to provoke unethical responses. PoATE crafts semantically opposing intents and integrates them with adversarial templates, steering models toward harmful outputs with remarkable subtlety. To counter this, we propose Intent-Aware CoT and Reverse Thinking CoT, which decompose queries to detect malicious intent and reason in reverse to evaluate and reject harmful responses.
  arXiv  Detail & Related papers  (2025-01-03T15:40:03Z)
• Transferable Adversarial Attacks on SAM and Its Downstream Models [87.23908485521439]
  This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM) To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm.
  arXiv  Detail & Related papers  (2024-10-26T15:04:04Z)
• Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data [29.842087372804905]
  This paper addresses the challenges of backdoor attack countermeasures in real-world scenarios. We propose a robust and clean-data-free backdoor defense framework, namely Mellivora Capensis (textttMeCa), which enables the model trainer to train a clean model on the poisoned dataset.
  arXiv  Detail & Related papers  (2024-05-21T12:20:19Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation [56.622250514119294]
  In contrast to white-box adversarial attacks, transfer attacks are more reflective of real-world scenarios. We propose a self-augment-based transfer attack method, termed SA-Attack.
  arXiv  Detail & Related papers  (2023-12-08T09:08:50Z)
• Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Data [19.579837693614326]
  We propose CAA, the first efficient evasion attack for constrained deep learning models. We leverage CAA to build a benchmark of deep tabular models across three popular use cases: credit scoring, phishing and botnet attacks detection.
  arXiv  Detail & Related papers  (2023-11-08T07:35:28Z)
• Unveiling Safety Vulnerabilities of Large Language Models [4.562678399685183]
  This paper introduces a unique dataset containing adversarial examples in the form of questions, which we call AttaQ. We assess the efficacy of our dataset by analyzing the vulnerabilities of various models when subjected to it. We introduce a novel automatic approach for identifying and naming vulnerable semantic regions.
  arXiv  Detail & Related papers  (2023-11-07T16:50:33Z)
• Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models [4.286570387250455]
  deep learning (DL) models can effectively learn city-wide crowd-flow patterns. DL models have been known to perform poorly on inconspicuous adversarial perturbations.
  arXiv  Detail & Related papers  (2023-03-05T13:30:25Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles [69.9674326582747]
  This paper presents a visual framework to investigate neural network models subjected to adversarial examples. We show how observing these elements can quickly pinpoint exploited areas in a model.
  arXiv  Detail & Related papers  (2021-03-18T13:04:21Z)
• Detection Defense Against Adversarial Attacks with Saliency Map [7.736844355705379]
  It is well established that neural networks are vulnerable to adversarial examples, which are almost imperceptible on human vision. Existing defenses are trend to harden the robustness of models against adversarial attacks. We propose a novel method combined with additional noises and utilize the inconsistency strategy to detect adversarial examples.
  arXiv  Detail & Related papers  (2020-09-06T13:57:17Z)

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.