Lucene search
+L

4522 matches found

Packet Storm News
Packet Storm News
added 2025/08/20 12:0 a.m.7 views

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...

6.8AI score
SaveExploits0
CNNVD
CNNVD
added 2025/08/20 12:0 a.m.11 views

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...

9CVSS7.2AI score0.0094EPSS
SaveExploits1References6
NVD
NVD
added 2025/08/19 2:15 p.m.10 views

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...

6.5CVSS0.00496EPSS
SaveExploits1References5
CVE
CVE
added 2025/08/19 12:0 a.m.29 views

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 ...

6.5CVSS7.5AI score0.00496EPSS
SaveExploits1References5
Packet Storm News
Packet Storm News
added 2025/08/19 12:0 a.m.6 views

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...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/19 12:0 a.m.7 views

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...

7.7AI score
SaveExploits0
CNNVD
CNNVD
added 2025/08/18 12:0 a.m.15 views

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...

8.7CVSS6.7AI score0.00472EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
added 2025/08/18 12:0 a.m.19 views

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...

7.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/18 12:0 a.m.7 views

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...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/18 12:0 a.m.7 views

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,...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/16 12:0 a.m.7 views

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...

7.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/16 12:0 a.m.7 views

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...

7.1AI score
SaveExploits0
Tenable Nessus
Tenable Nessus
added 2025/08/15 12:0 a.m.8 views

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...

7.5CVSS7.2AI score0.00593EPSS
SaveExploits1References2
Packet Storm News
Packet Storm News
added 2025/08/15 12:0 a.m.9 views

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...

6.8AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/08/14 6:52 p.m.6 views

Malicious code in yobi-models (npm)

The package yobi-models was found to contain malicious code...

7AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/08/14 6:52 p.m.5 views

Malicious code in sequelize-models-version-history (npm)

The package sequelize-models-version-history was found to contain malicious code...

7AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/08/14 6:52 p.m.3 views

Malicious code in models-frontend (npm)

The package models-frontend was found to contain malicious code...

7AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/08/14 6:52 p.m.3 views

Malicious code in elprices-models (npm)

The package elprices-models was found to contain malicious code...

7AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/08/14 6:52 p.m.4 views

Malicious code in humanapi-models (npm)

The package humanapi-models was found to contain malicious code...

7AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
added 2025/08/14 6:52 p.m.3 views

Malicious code in priv-models (npm)

The package priv-models was found to contain malicious code...

7AI score
SaveExploits0
Rows per page
Query Builder