Towards Understanding the Cognitive Habits of Large Reasoning Models

Large Reasoning Models LRMs, which autonomously produce a reasoning Chain of Thought CoT before producing final responses, offer a promising approach to interpreting and monitoring model behaviors. Inspired by the observation that certain CoT patterns -- e.g., "Wait, did I miss anything?'' --...

LB-LINK多款产品 安全漏洞

LB-LINK BL-X26 and others are products of China Bilink LB-LINK.LB-LINK BL-X26 is a wireless router.LB-LINK BL-LTE300 is a wireless router.LB-LINK BL-AC2100 is a wireless Wi-Fi 6 router. A security vulnerability exists in several LB-LINK products, which stems from a command injection in the cmd...

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models

As Diffusion Models DM generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the single-domain of initial Gaussian noise for generation, which...

TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems

Federated Learning has emerged as a privacy-oriented alternative to centralized Machine Learning, enabling collaborative model training without direct data sharing. While extensively studied for neural networks, the security and privacy implications of tree-based models remain underexplored. This...

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR

Extended reality XR systems, which consist of virtual reality VR, augmented reality AR, and mixed reality XR, offer a transformative interface for immersive, multi-modal, and embodied human-computer interaction. In this paper, we envision that multi-modal multi-task M3T federated foundation model...

A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarks

We present a novel attack specifically designed against Tree-Ring, a watermarking technique for diffusion models known for its high imperceptibility and robustness against removal attacks. Unlike previous removal attacks, which rely on strong assumptions about attacker capabilities, our attack on...

SoK: Evaluating Jailbreak Guardrails for Large Language Models

Large Language Models LLMs have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety mechanisms. Guardrails--external defense mechanisms that monitor and control LLM interaction--have emerged as a promisi...

User Perceptions and Attitudes toward Untraceability in Messaging Platforms

Mainstream messaging platforms offer a variety of features designed to enhance user privacy, such as disappearing messages, password-protected chats, and end-to-end encryption E2EE, which primarily protect message contents. Beyond contents, the transmission of messages generates metadata that can...

MAYA: Addressing Inconsistencies in Generative Password Guessing through a Unified Benchmark

Recent advances in generative models have led to their application in password guessing, with the aim of replicating the complexity, structure, and patterns of human-created passwords. Despite their potential, inconsistencies and inadequate evaluation methodologies in prior research have hindered...

[SECURITY] Fedora 42 Update: qt6-qtscxml-6.9.1-1.fc42

The Qt SCXML module provides functionality to create state machines from SCXM L files. This includes both dynamically creating state machines loading the SCXML file and instantiating states and transitions and generating a C++ file that has a class implementing the state machine. It also contains...

Design Patterns for Securing LLM Agents against Prompt Injections

As AI agents powered by Large Language Models LLMs become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on...

编号撤回

update is a library from Aaron's personal developer. serve is a PyTorch open source application for provisioning, optimizing, and scaling PyTorch models in production. This CVE number has been withdrawn...

ELFuzz: Efficient Input Generation Via LLM-Driven Synthesis over Fuzzer Space

Generation-based fuzzing produces appropriate testing cases according to specifications of input grammars and semantic constraints to test systems and software. However, these specifications require significant manual efforts to construct. This paper proposes a new approach, ELFuzz Evolution...

AI-Based Software Vulnerability Detection: a Systematic Literature Review

Software vulnerabilities in source code pose serious cybersecurity risks, prompting a shift from traditional detection methods e.g., static analysis, rule-based matching to AI-driven approaches. This study presents a systematic review of software vulnerability detection SVD research from 2018 to...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

CVE-2025-40567

A vulnerability has been identified in RUGGEDCOM RST2428P 6GK6242-6PA00 All versions V3.2, SCALANCE XCH328 6GK5328-4TS01-2EC2 All versions V3.2, SCALANCE XCM324 6GK5324-8TS01-2AC2 All versions V3.2, SCALANCE XCM328 6GK5328-4TS01-2AC2 All versions V3.2, SCALANCE XCM332 6GK5332-0GA01-2AC2 All...

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing

Diffusion models DMs have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright infringement. Concept erasing finetunes weights to unlearn...

TimeWak: Temporal Chained-Hashing Watermark for Time Series Data

Synthetic time series generated by diffusion models enable sharing privacy-sensitive datasets, such as patients' functional MRI records. Key criteria for synthetic data include high data utility and traceability to verify the data source. Recent watermarking methods embed in homogeneous latent...

DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt

Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...

Siemens多款产品 安全漏洞

Siemens RUGGEDCOM ROX MX5000 and others are products of Siemens, Germany Siemens.Siemens RUGGEDCOM ROX MX5000 is a communication device.Siemens RUGGEDCOM ROX RX1400 is a communication device.Siemens RUGGEDCOM ROX MX5000RE is a communication device. A security vulnerability exists in various Sieme...