5061 matches found
DrAttack
DrAttack: Prompt Decomposition and Reconstruction Makes Powerf...
JPRO: Automated Multimodal Jailbreaking Via Multi-Agent Collaboration Framework
The widespread application of large VLMs makes ensuring their secure deployment critical. While recent studies have demonstrated jailbreak attacks on VLMs, existing approaches are limited: they require either white-box access, restricting practicality, or rely on manually crafted patterns, leadin...
EASE: Practical and Efficient Safety Alignment for Small Language Models
Small language models SLMs are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While...
KG-DF: A Black-Box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
With the widespread application of large language models LLMs in various fields, the security challenges they face have become increasingly prominent, especially the issue of jailbreak. These attacks induce the model to generate erroneous or uncontrolled outputs through crafted inputs, threatenin...
Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic
Microsoft has disclosed details of a novel side-channel attack targeting remote language models that could enable a passive adversary with capabilities to observe network traffic to glean details about model conversation topics despite encryption protections under certain circumstances. This...
CVE-2020-36870 Ruijie Gateway EG & NBR Models v11.1(6)B9P1 - 11.9(4)B12P1 RCE
Various Ruijie Gateway EG and NBR models firmware versions 11.16B9P1 11.94B12P1 contain a code execution vulnerability in the EWEB management system that can be abused via front-end functionality. Attackers can exploit front-end code when features such as guest authentication, local server...
Whisper Leak: A novel side-channel attack on remote language models
Microsoft has discovered a new type of side-channel attack on remote language models. This type of side-channel attack could allow a cyberattacker a position to observe your network traffic to conclude language model conversation topics, despite being end-to-end encrypted via Transport Layer...
Whisper Leak: A novel side-channel attack on remote language models
Microsoft has discovered a new type of side-channel attack on remote language models. This type of side-channel attack could allow a cyberattacker a position to observe your network traffic to conclude language model conversation topics, despite being end-to-end encrypted via Transport Layer...
[SECURITY] Fedora 42 Update: GeographicLib-2.5.2-1.fc42
GeographicLib is a small set of C++ classes for performing conversions between geographic, UTM, UPS, MGRS, geocentric, and local Cartesian coordinates, for gravity e.g., EGM2008, geoid height and geomagnetic field e.g., WMM2010 calculations, and for solving geodesic problems. The emphasis is on...
Quantifying the Risk of Transferred Black Box Attacks
Neural networks have become pervasive across various applications, including security-related products. However, their widespread adoption has heightened concerns regarding vulnerability to adversarial attacks. With emerging regulations and standards emphasizing security, organizations must...
[SECURITY] Fedora 42 Update: qt5-qtscxml-5.15.18-1.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...
Large Language Models for Cyber Security
This paper studies the integration off Large Language Models into cybersecurity tools and protocols. The main issue discussed in this paper is how traditional rule-based and signature based security systems are not enough to deal with modern AI powered cyber threats. Cybersecurity industry is...
Explaining Software Vulnerabilities with Large Language Models
The prevalence of security vulnerabilities has prompted companies to adopt static application security testing SAST tools for vulnerability detection. Nevertheless, these tools frequently exhibit usability limitations, as their generic warning messages do not sufficiently communicate important...
CVE-2025-54323
An issue was discovered in the camera in Samsung Mobile Processor Exynos 980, 990, 850, 1080, 2100, 1280, 2200, 1330, 1380, 1480, 2400, and 1580. Improper debug printing leads to information leakage...
Specification-Guided Vulnerability Detection with Large Language Models
Large language models LLMs have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to distinguish vulnerable code from patched code. We argue that LLMs lack understanding of security specifications -- the...
Lexmark Printers Improper Input Validation (CVE-2019-6489)
Certain Lexmark CX, MX, X, XC, XM, XS, and 6500e devices before 2019-02-11 allow remote attackers to erase stored shortcuts. This plugin only works with Tenable.ot. Please visit https://www.tenable.com/products/tenable-ot for more information. %NASLMINLEVEL 80900 C Tenable, Inc...
Whisper Leak: A Side-Channel Attack on Large Language Models
Large Language Models LLMs are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that infers user prompt topics from encrypted LLM traffic by...
CVE-2025-52910
An issue was discovered in the GPU in Samsung Mobile Processor and Wearable Processor Exynos 1280, 2200, 1330, 1380, 1480, 2400. A Use-After-Free leads to privilege escalation...