Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks

While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introduce unnatural, high-frequency visual artifacts, while latent-space frameworks are confined by the limited search space of low-dimensional manifolds and inherent reconstruction flaws. To resolve these limitations, we propose Latent Geometric Chords (LGC) for Query-Efficient Decision-Based Adversarial Attacks alongside a variant, LGC-H. At its core, LGC navigates decision boundaries by executing a curvature-aware geometric search within a compressed semantic manifold. To guarantee high visual fidelity and circumvent dimensionality bottlenecks, we introduce a Residual-based Adversarial Generation (RAG) mechanism. RAG isolates semantic perturbations as geometric chords and superimposes them directly onto the original source image. RAG substantially resolves baseline reconstruction flaws and effectively doubles the permissible search space dimensions. Experimental results demonstrate that LGC achieves robust cross-dataset transferability and substantially outperforms state-of-the-art baselines. Notably, our method, LGC, minimizes perturbation magnitudes while achieving state-of-the-art visual fidelity--with a Structural Similarity Index Measure (SSIM) exceeding 0.99 and a Learned Perceptual Image Patch Similarity (LPIPS) below 0.01 at 5000 queries--and sustaining high attack success rates under stringent perceptual constraints, successfully compromising adversarially trained robust models. The source code is available at: https://github.com/eihmuekhine/Latent-Geometric-Chords.

• 01Low14%

  Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial P…

  The paper introduces PriceBlind, a white-box adversarial attack framework that d…
• 02Low13%

  Trans-RAG: Query-Centric Vector Transformation for Secure Cross-Organizational Retrieval

  Trans-RAG introduces a novel query-centric vector transformation technique to en…
• 03Low13%

  Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipul…

  The paper proposes AEGIS, a novel diffusion-guided method for injecting adversar…
• 04Low13%

  Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Bench…

  This paper provides the first comprehensive, end-to-end survey dedicated to the…
• 05Low13%

  REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models

  The paper introduces REFORGE, a black-box red-teaming framework that uses advers…
• 06Low12%

  Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions

  This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize…
• 07Low12%

  Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game

  The paper introduces CanaryRAG, a novel dual-path runtime defense mechanism that…
• 08Low12%

  PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Gener…

  The paper introduces PIDP-Attack, a novel compound adversarial attack that combi…