Target-driven Attack for Large Language Models

• URL: http://arxiv.org/abs/2411.07268v2
• Date: Wed, 13 Nov 2024 11:28:07 GMT
• Title: Target-driven Attack for Large Language Models
• Authors: Chong Zhang, Mingyu Jin, Dong Shu, Taowen Wang, Dongfang Liu, Xiaobo Jin,
• Abstract summary: We propose our target-driven black-box attack method to maximize the KL divergence between the conditional probabilities of clean text and the attack text. Experimental results on multiple Large Language Models and datasets demonstrate the effectiveness of our attack method.
• Score: 14.784132523066567
• License:
• Abstract: Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security challenges like the language model not giving the correct answer. Although there is currently a large amount of research on black-box attacks, most of these black-box attacks use random and heuristic strategies. It is unclear how these strategies relate to the success rate of attacks and thus effectively improve model robustness. To solve this problem, we propose our target-driven black-box attack method to maximize the KL divergence between the conditional probabilities of the clean text and the attack text to redefine the attack's goal. We transform the distance maximization problem into two convex optimization problems based on the attack goal to solve the attack text and estimate the covariance. Furthermore, the projected gradient descent algorithm solves the vector corresponding to the attack text. Our target-driven black-box attack approach includes two attack strategies: token manipulation and misinformation attack. Experimental results on multiple Large Language Models and datasets demonstrate the effectiveness of our attack method.

Related papers

• A Realistic Threat Model for Large Language Model Jailbreaks [87.64278063236847]
  In this work, we propose a unified threat model for the principled comparison of jailbreak attacks. Our threat model combines constraints in perplexity, measuring how far a jailbreak deviates from natural text. We adapt popular attacks to this new, realistic threat model, with which we, for the first time, benchmark these attacks on equal footing.
  arXiv  Detail & Related papers  (2024-10-21T17:27:01Z)
• Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models [29.1607388062023]
  This paper focuses on a challenging scenario: decision-based black-box targeted attacks where the attackers only have access to the final output text and aim to perform targeted attacks. A three-stage process textitAsk, Attend, Attack, called textitAAA, is proposed to coordinate with the solver. Experimental results on transformer-based and CNN+RNN-based image-to-text models confirmed the effectiveness of our proposed textitAAA
  arXiv  Detail & Related papers  (2024-08-16T19:35:06Z)
• Learning diverse attacks on large language models for robust red-teaming and safety tuning [126.32539952157083]
  Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe deployment of large language models. We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks. We propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts.
  arXiv  Detail & Related papers  (2024-05-28T19:16:17Z)
• Goal-guided Generative Prompt Injection Attack on Large Language Models [6.175969971471705]
  Large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface. It is unclear how these strategies relate to the success rate of attacks and thus effectively improve model security.
  arXiv  Detail & Related papers  (2024-04-06T06:17:10Z)
• Transferable Attack for Semantic Segmentation [59.17710830038692]
  adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. We propose an ensemble attack for semantic segmentation to achieve more effective attacks with higher transferability.
  arXiv  Detail & Related papers  (2023-07-31T11:05:55Z)
• Versatile Weight Attack via Flipping Limited Bits [68.45224286690932]
  We study a novel attack paradigm, which modifies model parameters in the deployment stage. Considering the effectiveness and stealthiness goals, we provide a general formulation to perform the bit-flip based weight attack. We present two cases of the general formulation with different malicious purposes, i.e., single sample attack (SSA) and triggered samples attack (TSA)
  arXiv  Detail & Related papers  (2022-07-25T03:24:58Z)
• Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection [89.08832589750003]
  We propose a Parallel Rectangle Flip Attack (PRFA) via random search to avoid sub-optimal detection near the attacked region. Our method can effectively and efficiently attack various popular object detectors, including anchor-based and anchor-free, and generate transferable adversarial examples.
  arXiv  Detail & Related papers  (2022-01-22T06:00:17Z)
• Multi-granularity Textual Adversarial Attack with Behavior Cloning [4.727534308759158]
  We propose MAYA, a Multi-grAnularitY Attack model to generate high-quality adversarial samples with fewer queries to victim models. We conduct comprehensive experiments to evaluate our attack models by attacking BiLSTM, BERT and RoBERTa in two different black-box attack settings and three benchmark datasets.
  arXiv  Detail & Related papers  (2021-09-09T15:46:45Z)
• Towards Variable-Length Textual Adversarial Attacks [68.27995111870712]
  It is non-trivial to conduct textual adversarial attacks on natural language processing tasks due to the discreteness of data. In this paper, we propose variable-length textual adversarial attacks(VL-Attack) Our method can achieve $33.18$ BLEU score on IWSLT14 German-English translation, achieving an improvement of $1.47$ over the baseline model.
  arXiv  Detail & Related papers  (2021-04-16T14:37:27Z)

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.