Related papers: Authenticated Contradictions from Desynchronized P…

Advanced Persistent Threats (APTs) are sophisticated, targeted cyberattacks designed to gain unauthorized access to systems and remain undetected for extended periods. To evade detection, APT cyberattacks deceive defense layers with…

The Deepfake technology has raised serious concerns regarding privacy breaches and trust issues. To tackle these challenges, Deepfake detection technology has emerged. Current methods over-rely on the global feature space, which contains…

Advances in graphics and machine learning have led to the general availability of easy-to-use tools for modifying and synthesizing media. The proliferation of these tools threatens to cast doubt on the veracity of all media. One approach to…

Watermarking AI-generated text is critical for combating misuse. Yet recent theoretical work argues that any watermark can be erased via random walk attacks that perturb text while preserving quality. However, such attacks rely on two key…

Convolutional neural network based face forgery detection methods have achieved remarkable results during training, but struggled to maintain comparable performance during testing. We observe that the detector is prone to focus more on…

Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires the identification of the disentangled latent…

Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…

Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently…

Side-channel attacks are a major threat to the security of cryptosystems. Masking is a widely used countermeasure against such attacks, but proving the security of masked algorithms is error-prone without formal verification. In this work,…

Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content provenance and attribution. The growing complexity of digital…

Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in…

The proliferation of autonomous software agents necessitates rigorous frameworks for establishing secure and verifiable agent-to-agent (A2A) interactions, particularly when such agents are instantiated as non-human identities(NHIs). We…

Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…

The advent of Federated Learning (FL) as a distributed machine learning paradigm has introduced new cybersecurity challenges, notably adversarial attacks that threaten model integrity and participant privacy. This study proposes an…

Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models…

Generative models have enabled easy creation and generation of images of all kinds given a single prompt. However, this has also raised ethical concerns about what is an actual piece of content created by humans or cameras compared to…

Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g., ROUGE) and embedding-based measures (e.g., BERTScore), often misjudge semantic…

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…

We propose a watermarking method for protecting the Intellectual Property (IP) of Generative Adversarial Networks (GANs). The aim is to watermark the GAN model so that any image generated by the GAN contains an invisible watermark…

The proliferation of autoregressive (AR) image generators demands reliable detection and attribution of their outputs to mitigate misinformation, and to filter synthetic images from training data to prevent model collapse. To address this…