Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

• URL: http://arxiv.org/abs/2508.14853v1
• Date: Wed, 20 Aug 2025 17:03:32 GMT
• Title: Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent
• Authors: Sajib Biswas, Mao Nishino, Samuel Jacob Chacko, Xiuwen Liu,
• Abstract summary: Large language models (LLMs) are increasingly deployed in critical applications.<n>LLMs remain vulnerable to jailbreak attacks enabled by crafted adversarial triggers appended to user prompts.<n>We propose an intrinsic optimization method which directly optimize relaxed one-hot encodings of the adversarial suffix tokens.
• Score: 1.1187085721899017
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning from human feedback (RLHF) on typical prompts, LLMs remain vulnerable to jailbreak attacks enabled by crafted adversarial triggers appended to user prompts. Most existing jailbreak methods either rely on inefficient searches over discrete token spaces or direct optimization of continuous embeddings. While continuous embeddings can be given directly to selected open-source models as input, doing so is not feasible for proprietary models. On the other hand, projecting these embeddings back into valid discrete tokens introduces additional complexity and often reduces attack effectiveness. We propose an intrinsic optimization method which directly optimizes relaxed one-hot encodings of the adversarial suffix tokens using exponentiated gradient descent coupled with Bregman projection, ensuring that the optimized one-hot encoding of each token always remains within the probability simplex. We provide theoretical proof of convergence for our proposed method and implement an efficient algorithm that effectively jailbreaks several widely used LLMs. Our method achieves higher success rates and faster convergence compared to three state-of-the-art baselines, evaluated on five open-source LLMs and four adversarial behavior datasets curated for evaluating jailbreak methods. In addition to individual prompt attacks, we also generate universal adversarial suffixes effective across multiple prompts and demonstrate transferability of optimized suffixes to different LLMs.

Related papers

• Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks [22.52730333160258]
  We introduce RAILS, a framework that operates solely on model logits.<n>By eliminating gradient dependency, RAILS enables cross-tokenizer ensemble attacks.<n> Empirically, RAILS achieves near 100% success rates on multiple open-source models and high black-box attack transferability to closed-source systems like GPT and Gemini.
  arXiv  Detail & Related papers  (2026-01-06T21:14:13Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• VERA: Variational Inference Framework for Jailbreaking Large Language Models [29.57412296290215]
  API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods.<n>We introduce VERA: Variational infErence fRamework for jAilbreaking.
  arXiv  Detail & Related papers  (2025-06-27T22:22:00Z)
• Adversarial Attack on Large Language Models using Exponentiated Gradient Descent [1.1187085721899017]
  Large Language Models are vulnerable to jailbreaking attacks.<n>We develop an intrinsic optimization technique using exponentiated gradient descent.<n>We show that the technique achieves a higher success rate with great efficiency compared to three other state-of-the-art jailbreaking techniques.
  arXiv  Detail & Related papers  (2025-05-14T21:50:46Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• Prefill-Based Jailbreak: A Novel Approach of Bypassing LLM Safety Boundary [2.4329261266984346]
  Large Language Models (LLMs) are designed to generate helpful and safe content.<n> adversarial attacks, commonly referred to as jailbreak, can bypass their safety protocols.<n>We introduce a novel jailbreak attack method that leverages the prefilling feature of LLMs.
  arXiv  Detail & Related papers  (2025-04-28T07:38:43Z)
• LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds [98.20826635707341]
  Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts.<n>We frame jailbreaks as inference-time misalignment and introduce LIAR, a fast, black-box, best-of-$N$ sampling attack requiring no training.<n>We also introduce a theoretical "safety net against jailbreaks" metric to quantify safety alignment strength and derive suboptimality bounds.
  arXiv  Detail & Related papers  (2024-12-06T18:02:59Z)
• GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs [3.096869664709865]
  We introduce Generative Adversarial Suffix Prompter (GASP), a novel framework that can efficiently generate human-readable jailbreak prompts.<n>We show that GASP can produce natural adversarial prompts, significantly improving jailbreak success over baselines, reducing training times, and accelerating inference speed.
  arXiv  Detail & Related papers  (2024-11-21T14:00:01Z)
• Adversarial Attacks on Large Language Models Using Regularized Relaxation [1.042748558542389]
  Large Language Models (LLMs) are used for numerous practical applications. adversarial attack methods are extensively used to study and understand these vulnerabilities. We propose a novel technique for adversarial attacks that overcomes these limitations by leveraging regularized gradients with continuous optimization methods.
  arXiv  Detail & Related papers  (2024-10-24T21:01:45Z)
• Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings [57.136748215262884]
  We introduce ObscurePrompt for jailbreaking LLMs, inspired by the observed fragile alignments in Out-of-Distribution (OOD) data.<n>We first formulate the decision boundary in the jailbreaking process and then explore how obscure text affects LLM's ethical decision boundary.<n>Our approach substantially improves upon previous methods in terms of attack effectiveness, maintaining efficacy against two prevalent defense mechanisms.
  arXiv  Detail & Related papers  (2024-06-19T16:09:58Z)
• Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization [46.98249466236357]
  Large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content.<n>This paper introduces a novel token-level attack method, Adaptive-to-Sparse Constrained Optimization (ADC), which has been shown to successfully jailbreak multiple open-source LLMs.
  arXiv  Detail & Related papers  (2024-05-15T06:11:24Z)
• ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings [58.82536530615557]
  We propose an Adversarial Suffix Embedding Translation Framework (ASETF) to transform continuous adversarial suffix embeddings into coherent and understandable text. Our method significantly reduces the computation time of adversarial suffixes and achieves a much better attack success rate to existing techniques.
  arXiv  Detail & Related papers  (2024-02-25T06:46:27Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)

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.