Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution

• URL: http://arxiv.org/abs/2603.01784v1
• Date: Mon, 02 Mar 2026 12:10:46 GMT
• Title: Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution
• Abstract summary: We move beyond static adversarial supervision and introduce co-evolutionary alignment with evolving attacks.<n>We introduce an Evolutionary Attacker that decomposes adversarial prompts into method templates and harmful intents.<n>The Adaptive Defender is iteratively updated on the synthesized hard negatives, forming a closed-loop process that adapts alignment to evolving attacks.
• Score: 8.28457465201508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on static adversarial settings, which fundamentally limit robustness, particularly in multimodal settings with a larger attack surface. In this work, we move beyond static adversarial supervision and introduce co-evolutionary alignment with evolving attacks, instantiated by CEMMA (Co-Evolutionary Multi-Modal Alignment), an automated and adaptive framework for multimodal safety alignment. We introduce an Evolutionary Attacker that decomposes adversarial prompts into method templates and harmful intents. By employing genetic operators, including mutation, crossover, and differential evolution, it enables simple seed attacks to inherit the structural efficacy of sophisticated jailbreaks. The Adaptive Defender is iteratively updated on the synthesized hard negatives, forming a closed-loop process that adapts alignment to evolving attacks. Experiments show that the Evolutionary Attacker substantially increases red-teaming jailbreak attack success rate (ASR), while the Adaptive Defender improves robustness and generalization across benchmarks with higher data efficiency, without inducing excessive benign refusal, and remains compatible with inference-time defenses such as AdaShield.

Related papers

• A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks [53.12252890906191]
  Large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose a self-evolving test-time defense built around a persistent, cross-interaction rule memory.
  arXiv  Detail & Related papers  (2026-08-26T16:52:06Z)
• Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks [56.45762972211923]
  We present a proactive defense framework for securing LLMs against evolving multi-turn adversarial attacks.<n>It employs a cooperative multi-agent architecture in which specialized agents execute complementary defense strategies.<n>We present the EMRA dataset designed to simulate evolving strategies across multi-turn attacks.
  arXiv  Detail & Related papers  (2026-07-31T14:04:49Z)
• Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs [56.53007443197966]
  Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks.<n>Their explicit chain-of-thought (CoT) mechanism introduces new security risks, making them particularly vulnerable to jailbreak attacks.<n>We propose an adaptive evolutionary CoT jailbreak framework, called AE-CoT, to overcome these limitations.
  arXiv  Detail & Related papers  (2026-05-23T10:11:32Z)
• NAAMSE: Framework for Evolutionary Security Evaluation of Agents [1.0131895986034316]
  We propose NAAMSE, an evolutionary framework that reframes agent security evaluation as a feedback-driven optimization problem.<n>Our system employs a single autonomous agent that orchestrates a lifecycle of genetic prompt mutation, hierarchical corpus exploration, and asymmetric behavioral scoring.<n>Experiments on Gemini 2.5 Flash demonstrate that evolutionary mutation systematically amplifies vulnerabilities missed by one-shot methods.
  arXiv  Detail & Related papers  (2026-02-07T06:13:02Z)
• Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference [45.723695657400576]
  We argue that enhancing the diversity and coverage of counterattacks is crucial to improving adversarial robustness in test-time defense.<n>We propose Directional Orthogonal Counterattack (DOC), which augments counterattack optimization by incorporating gradient directions and momentum-based updates.<n>We present a directional sensitivity score based on averaged cosine similarity to boost DOC by improving example discrimination and adaptively modulating the counterattack strength.
  arXiv  Detail & Related papers  (2025-11-12T07:40:16Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints [2.139012072214621]
  Federated Learning (FL) is increasingly adopted for privacy-preserving collaborative training, but its decentralized nature makes it susceptible to backdoor attacks.<n>Existing attack methods, however, often rely on idealized assumptions and fail to remain effective under real-world constraints.<n>We propose DOPA, a novel framework that simulates heterogeneous local training dynamics and seeks consensus across divergent optimization trajectories to craft universally effective and stealthy backdoor triggers.
  arXiv  Detail & Related papers  (2025-08-20T08:39:12Z)
• CyGATE: Game-Theoretic Cyber Attack-Defense Engine for Patch Strategy Optimization [73.13843039509386]
  This paper presents CyGATE, a game-theoretic framework modeling attacker-defender interactions.<n>CyGATE frames cyber conflicts as a partially observable game (POSG) across Cyber Kill Chain stages.<n>The framework's flexible architecture enables extension to multi-agent scenarios.
  arXiv  Detail & Related papers  (2025-08-01T09:53:06Z)
• Improving Black-Box Generative Attacks via Generator Semantic Consistency [51.470649503929344]
  generative attacks produce adversarial examples in a single forward pass at test time.<n>We enforce semantic consistency by aligning the early generator's intermediate features to an EMA teacher.<n>Our approach can be seamlessly integrated into existing generative attacks with consistent improvements in black-box transfer.
  arXiv  Detail & Related papers  (2025-06-23T02:35:09Z)
• Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks [62.036798488144306]
  Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. We propose an attack-agnostic defense method named Meta Invariance Defense (MID) We show that MID simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration.
  arXiv  Detail & Related papers  (2024-04-04T10:10:38Z)
• Multi-granular Adversarial Attacks against Black-box Neural Ranking Models [111.58315434849047]
  We create high-quality adversarial examples by incorporating multi-granular perturbations. We transform the multi-granular attack into a sequential decision-making process. Our attack method surpasses prevailing baselines in both attack effectiveness and imperceptibility.
  arXiv  Detail & Related papers  (2024-04-02T02:08:29Z)
• Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations [1.9100854225243937]
  We propose a novel method called multi-objective evolutionary search of variable-length composite semantic perturbations (MES-VCSP) MES-VCSP can obtain adversarial examples with a higher attack success rate, more naturalness, and less time cost.
  arXiv  Detail & Related papers  (2023-07-13T04:08:16Z)
• Adaptive Feature Alignment for Adversarial Training [56.17654691470554]
  CNNs are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. We propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our method is trained to automatically align features of arbitrary attacking strength.
  arXiv  Detail & Related papers  (2021-05-31T17:01:05Z)

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.