Sandcastles in the Storm: Revisiting the (Im)Possibility of Strong Watermarking

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 assumptions: 1 rapid mixing watermarks dissolve quickly...

NCorr-FP: a Neighbourhood-Based Correlation-Preserving Fingerprinting Scheme for Intellectual Property Protection of Structured Data

Ensuring data ownership and traceability of unauthorised redistribution are central to safeguarding intellectual property in shared data environments. Data fingerprinting addresses these challenges by embedding recipient-specific marks into the data, typically via content modifications. We propos...

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Most existing unlearnable strategies focus on preventing unauthorized users from training single-task learning STL models with personal data. Nevertheless, the paradigm has recently shifted towards multi-task data and multi-task learning MTL, targeting generalist and foundation models that can...

RAP-SM: Robust Adversarial Prompt Via Shadow Models for Copyright Verification of Large Language Models

Recent advances in large language models LLMs have underscored the importance of safeguarding intellectual property rights through robust fingerprinting techniques. Traditional fingerprint verification approaches typically focus on a single model, seeking to improve the robustness of its...

Dynamic Graph-Based Fingerprinting of In-Browser Cryptomining

The decentralized and unregulated nature of cryptocurrencies, combined with their monetary value, has made them a vehicle for various illicit activities. One such activity is cryptojacking, an attack that uses stolen computing resources to mine cryptocurrencies without consent for profit...

Network Attack Traffic Detection with Hybrid Quantum-Enhanced Convolution Neural Network

The emerging paradigm of Quantum Machine Learning QML combines features of quantum computing and machine learning ML. QML enables the generation and recognition of statistical data patterns that classical computers and classical ML methods struggle to effectively execute. QML utilizes quantum...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

GTSD: Generative Text Steganography Based on Diffusion Model

With the rapid development of deep learning, existing generative text steganography methods based on autoregressive models have achieved success. However, these autoregressive steganography approaches have certain limitations. Firstly, existing methods require encoding candidate words according t...

FCGHunter: Towards Evaluating Robustness of Graph-Based Android Malware Detection

Graph-based detection methods leveraging Function Call Graphs FCGs have shown promise for Android malware detection AMD due to their semantic insights. However, the deployment of malware detectors in dynamic and hostile environments raises significant concerns about their robustness. While recent...

Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations

This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of various adversarial attack strategies on model performance...

AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...

How Private Is Your Attention? Bridging Privacy with In-Context Learning

In-context learning ICL-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms underlying ICL, its feasibility under formal privacy constraints...

PT-Mark: Invisible Watermarking for Text-To-Image Diffusion Models Via Semantic-Aware Pivotal Tuning

Watermarking for diffusion images has drawn considerable attention due to the widespread use of text-to-image diffusion models and the increasing need for their copyright protection. Recently, advanced watermarking techniques, such as Tree Ring, integrate watermarks by embedding traceable pattern...

Important: kernel

Issue Overview: In the Linux kernel, the following vulnerability has been resolved: block, bfq: don't move oombfqq CVE-2022-49179 In the Linux kernel, the following vulnerability has been resolved: macsec: fix UAF bug for realdev CVE-2022-49390 In the Linux kernel, the following vulnerability has...

How to Enhance Downstream Adversarial Robustness (Almost) without Touching the Pre-Trained Foundation Model?

With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only need to fine-tune and adapt it to specific downstream...

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Vision-language models VLMs, such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and the common practice of selecting from a limited set of...

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction

The large integration of microphones into devices increases the opportunities for Acoustic Side-Channel Attacks ASCAs, as these can be used to capture keystrokes' audio signals that might reveal sensitive information. However, the current State-Of-The-Art SOTA models for ASCAs, including...

GHSA-CWRH-575J-8VR3 Karmada Tar Slips in CRDs archive extraction

Impact What kind of vulnerability is it? Who is impacted? Both in karmadactl and karmada-operator, it is possible to supply a filesystem path, or an HTTPs URL to retrieve the custom resource definitionsCRDs needed by karmada. The CRDs are downloaded as a gzipped tarfile and are vulnerable to a...

CVE-2024-53096

CVE-2024-53096: Linux kernel patch resolves faulty mmap_region() error path. Key changes move core logic into __mmap_region(), perform upfront validations, and unwind writable/ seal checks earlier. Effects include preallocating iterator state before file-backed hooks, early handling of mapping_ma...

CVE-2024-53096

In the Linux kernel, the following vulnerability has been resolved: mm: resolve faulty mmapregion error path behaviour The mmapregion function is somewhat terrifying, with spaghetti-like control flow and numerous means by which issues can arise and incomplete state, memory leaks and other...