4522 matches found
MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-Of-Experts LLMs
The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to scale explosively for performance, implementation efficiency remains a critical...
Linksys多款产品 安全漏洞
Linksys RE6300 and others are products of Linksys, Inc.Linksys RE6300 is a wireless network signal extender.Linksys RE6250 is a wireless extender.Linksys RE6350 is a wireless extender.Linksys RE6350 is a wireless extender.Linksys RE6350 is a wireless extender.Linksys RE6350 is a wireless...
CVE-2025-50461
A deserialization vulnerability exists in Volcengine's verl 3.0.0, specifically in the scripts/modelmerger.py script when using the "fsdp" backend. The script calls torch.load with weightsonly=False on user-supplied .pt files, allowing attackers to execute arbitrary code if a maliciously crafted...
CVE-2025-50461
CVE-2025-50461 describes a deserialization vulnerability in Volcengine Verl 3.0.0, specifically in scripts/model_merger.py when using the "fsdp" backend. The code calls torch.load() with weights_only=False on user-supplied .pt files, enabling arbitrary code execution if a malicious model file is ...
Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance
Targeted adversarial attacks are essential for proactively identifying security flaws in Vision-Language Models before real-world deployment. However, current methods perturb images to maximize global similarity with the target text or reference image at the encoder level, collapsing rich visual...
CCFC: Core and Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection
Jailbreak attacks pose a serious challenge to the safe deployment of large language models LLMs. We introduce CCFC Core & Core-Full-Core, a dual-track, prompt-level defense framework designed to mitigate LLMs' vulnerabilities from prompt injection and structure-aware jailbreak attacks. CCFC...
Schneider Electric多款产品 输入验证错误漏洞
The Schneider Electric Modicon M340 is a mid-range PLC programmable logic controller for industrial processes and infrastructure from Schneider Electric France. An input validation error vulnerability exists in various Schneider Electric products, which stems from improper input validation and...
Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
The advancement of AI technologies, particularly Large Language Models LLMs, has transformed computing while introducing new security and privacy risks. Prior research shows that cybercriminals are increasingly leveraging uncensored LLMs ULLMs as backends for malicious services. Understanding the...
VerilogLAVD: LLM-Aided Rule Generation for Vulnerability Detection in Verilog
Timely detection of hardware vulnerabilities during the early design stage is critical for reducing remediation costs. Existing early detection techniques often require specialized security expertise, limiting their usability. Recent efforts have explored the use of large language models LLMs for...
MAJIC: Markovian Adaptive Jailbreaking Via Iterative Composition of Diverse Innovative Strategies
Large Language Models LLMs have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking techniques primarily rely on static prompts crafted with a single,...
Mitigating Jailbreaks with Intent-Aware LLMs
Despite extensive safety-tuning, large language models LLMs remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose Intent-FT, a simple and lightweight fine-tuning approach that...
Unlearning at Scale: Implementing the Right to Be Forgotten in Large Language Models
We study the right to be forgotten GDPR Art. 17 for large language models and frame unlearning as a reproducible systems problem. Our approach treats training as a deterministic program and logs a minimal per-microbatch record ordered ID hash, RNG seed, learning-rate value, optimizer-step counter...
Ollama <= 0.3.3 DoS
The version of Ollama installed on the remote host is prior or equal to 0.3.3. It is, therefore, affected by a vulnerability. A divide by zero vulnerability exists in ollama/ollama version v0.3.3. The vulnerability occurs when importing GGUF models with a crafted type for blockcount in the...
CryptoScope: Utilizing Large Language Models for Automated Cryptographic Logic Vulnerability Detection
Cryptographic algorithms are fundamental to modern security, yet their implementations frequently harbor subtle logic flaws that are hard to detect. We introduce CryptoScope, a novel framework for automated cryptographic vulnerability detection powered by Large Language Models LLMs. CryptoScope...
Malicious code in yobi-models (npm)
The package yobi-models was found to contain malicious code...
Malicious code in sequelize-models-version-history (npm)
The package sequelize-models-version-history was found to contain malicious code...
Malicious code in models-frontend (npm)
The package models-frontend was found to contain malicious code...
Malicious code in elprices-models (npm)
The package elprices-models was found to contain malicious code...