microcode_ctl: From CVEorg collector

A flaw was found in the Branch Prediction Unit BPU of Intel's Lion Core CPUs that make it possible for an attacker to bypass Indirect Branch Predictor Barrier IBPB protections. By employing branch predictor training techniques as described in the "Training Solo" publication, an attacker with loca...

Autonomous Cyber Resilience Via a Co-Evolutionary Arms Race within a Fortified Digital Twin Sandbox

The convergence of IT and OT has created hyper-connected ICS, exposing critical infrastructure to a new class of adaptive, intelligent adversaries that render static defenses obsolete. Existing security paradigms often fail to address a foundational "Trinity of Trust," comprising the fidelity of...

Anti-Phishing Training Does Not Work: a Large-Scale Empirical Assessment of Multi-Modal Training Grounded in the NIST Phish Scale

Social engineering attacks using email, commonly known as phishing, are a critical cybersecurity threat. Phishing attacks often lead to operational incidents and data breaches. As a result, many organizations allocate a substantial portion of their cybersecurity budgets to phishing awareness...

DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?

Adversarial examples are small and often imperceptible perturbations crafted to fool machine learning models. These attacks seriously threaten the reliability of deep neural networks, especially in security-sensitive domains. Evasion attacks, a form of adversarial attack where input is modified a...

LLM Embedding-Based Attribution (LEA): Quantifying Source Contributions to Generative Model'S Response for Vulnerability Analysis

Security vulnerabilities are rapidly increasing in frequency and complexity, creating a shifting threat landscape that challenges cybersecurity defenses. Large Language Models LLMs have been widely adopted for cybersecurity threat analysis. When querying LLMs, dealing with new, unseen...

Shrinking the Generation-Verification Gap with Weak Verifiers

Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable e.g., humans or limited in utility e.g., tools like Lean. While LM judges and reward models have become broadly useful as...

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

Large vision-language models LVLMs have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used t...

Watermarking Quantum Neural Networks Based on Sample Grouped and Paired Training

Quantum neural networks QNNs leverage quantum computing to create powerful and efficient artificial intelligence models capable of solving complex problems significantly faster than traditional computers. With the fast development of quantum hardware technology, such as superconducting qubits,...

KCES: Training-Free Defense for Robust Graph Neural Networks Via Kernel Complexity

Graph Neural Networks GNNs have achieved impressive success across a wide range of graph-based tasks, yet they remain highly vulnerable to small, imperceptible perturbations and adversarial attacks. Although numerous defense methods have been proposed to address these vulnerabilities, many rely o...

SoK: the Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

Large language models LLMs are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer significant technological progress, their development using vast amounts of user data scraped from the web and collected from...

Unlearning-Enhanced Website Fingerprinting Attack: against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting WF is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website...

Don't Throw the Baby out with the Bathwater: How and Why Deep Learning for ARC

The Abstraction and Reasoning Corpus ARC-AGI presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful state-of-the-art neural networks NN across varied modalities and...

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments

With the growing integration of vision-language models VLMs, mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated datasets, leaving them vulnerable to covert threats during the training process...

LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data

Large language models LLMs can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset watermarking addresses this by embedding identifiable modification...

Private Training and Data Generation by Clustering Embeddings

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been shown to unintentionally memorize and reveal sensitive...

A Sea of Cyber Threats: Maritime Cybersecurity from the Perspective of Mariners

Maritime systems, including ships and ports, are critical components of global infrastructure, essential for transporting over 80% of the world's goods and supporting internet connectivity. However, these systems face growing cybersecurity threats, as shown by recent attacks disrupting Maersk, on...

DiffUMI: Training-Free Universal Model Inversion Via Unconditional Diffusion for Face Recognition

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which are traditionally viewed as privacy-preserving. However, model inversion...

Certified Unlearning for Neural Networks

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten." Unfortunately, existing methods rely on restrictive assumptio...

IF-GUIDE: Influence Function-Guided Detoxification of LLMs

We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained and potentially toxic models to align them with human values. In contrast, we propose a...

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models

Large Language Models LLMs memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information PII, which should not be stored and, consequently, not leaked. In this paper, we introduce Private Memorization Editing PME, an approach for preventing private...