The paper introduces a dual-dimension evaluation for universal adversarial attacks on Vision-Language Models (VLMs), demonstrating that high reported attack success rates significantly overestimate th…

This paper investigates a novel security vulnerability where imperceptible branding hints can be injected into images and subsequently re-rendered onto new objects by generative AI models, proposing b…

The paper proposes a unified, architecture-agnostic framework that significantly improves the robustness of deepfake image detectors against adversarial attacks by focusing on higher-order frequency s…

The paper proposes FLAME, a novel framework that detects AI-generated image forgeries by identifying intrinsic energy anomalies caused by the diffusion process, achieving state-of-the-art localization…

The paper introduces DiffusionHijack, a supply-chain backdoor attack that compromises the PRNG used by diffusion models to deterministically control generated images, which is successfully mitigated b…

The paper introduces SEED, a large-scale benchmark dataset for tracing sequential deepfake facial edits, and proposes FAITH, a frequency-aware Transformer model that effectively detects and orders the…

Dual-Guard introduces a dual-channel latent watermarking framework that simultaneously embeds global provenance and localized content anchors into diffusion images, achieving robust detection against…

The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature…

The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.

The paper demonstrates that off-the-shelf image diffusion models, like Stable Diffusion, can be repurposed to generate synthetic structured data, posing a threat of ground truth drift in closed eviden…

The paper proposes PCDM, a diffusion-based framework that enables highly stealthy and effective data poisoning attacks against Federated Learning systems, significantly degrading global performance wh…

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial def…

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…

The paper introduces SET, a robust input-level backdoor detection framework that detects hidden malicious triggers in text-to-image diffusion models by analyzing systematic differences in how benign a…

The paper introduces TGIF2, an extended dataset and benchmark that evaluates the forensic robustness of image forgery detection methods against modern, advanced text-guided inpainting techniques.

The paper introduces GenAI-FDIA, a comprehensive framework that benchmarks various physics-informed generative models to synthesize high-fidelity False Data Injection Attacks (FDIA) for power systems,…

The paper proposes Hydra, a framework to stabilize and control the injection of multiple, conflicting backdoor triggers into text-to-image diffusion models, ensuring high attack reliability while main…

The paper demonstrates that high detection performance against obfuscated prompts does not guarantee representational robustness, identifying a phenomenon called latent embedding collapse.

The paper introduces ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper introduces SHIFT, a training-free attack that exploits the vulnerability of diffusion-based watermarking by stochastically deflecting the generative trajectory, achieving high removal rates…