DeepSignature proposes a novel, cryptographically verifiable watermarking system that uses deep neural networks to embed digital signatures into images, enabling robust source attribution and near 100…

This paper proposes a 3D CNN detector that leverages temporal artifacts to accurately identify high-quality deepfake videos, demonstrating robust detection even after social media re-encoding.

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…

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 a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

The paper proposes evaluating certified training methods by comparing their Pareto fronts across the natural-certified accuracy trade-off, revealing superior performance and previously unappreciated c…

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

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 introduces a new dataset (SHDF) and a framework (T-AVFD) to robustly detect audio-visual deepfakes, specifically addressing the challenge posed by singing vocalizations.

The paper demonstrates a class of steganographic exfiltration attacks against vector databases by hiding data within embeddings, and proposes VectorPin, a cryptographic provenance protocol to detect s…

The paper proposes Cert-LAS, a novel certified method for verifying model ownership in text-to-image diffusion models, which is robust against malicious signal removal attacks.

The paper enhances the security of the PolyProtect biometric template protection method by proposing a key selection algorithm that significantly increases the difficulty of inverting protected face t…

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…

BIDO introduces a device-free, NIST AAL2-compliant biometric authentication standard that deterministically generates ephemeral ECDSA keys from live biometric measurements, eliminating the need for st…

TimeMark proposes a trustworthy time watermarking framework that uses cryptographic techniques and error-correcting codes to achieve 100% accurate recovery of the generation time from AIGC, resisting…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper demonstrates that combining outputs from multiple large language models (LLMs) effectively cancels out statistical watermarks, revealing a fundamental vulnerability in current AI text detect…

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

The paper introduces Compositional Semantic Fingerprinting (CSF), a black-box method that allows IP owners to attribute fine-tuned text-to-image models to their protected lineages using only query acc…