Lucene search
+L

5582 matches found

Packet Storm News
Packet Storm News
added 2025/05/29 12:00 a.m.23 views

LLM Agents Should Employ Security Principles

Large Language Model LLM agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of context manipulation introduce new vulnerabilities related to...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/28 12:00 a.m.12 views

Test-Time Immunization: a Universal Defense Framework against Jailbreaks for (Multimodal) Large Language Models

While multimodal large language models LLMs have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defense methods are proposed to defend against jailbreak attacks, however, they are often tailored to specific types of...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/27 12:00 a.m.10 views

System Prompt Extraction Attacks and Defenses in Large Language Models

The system prompt in Large Language Models LLMs plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/26 12:00 a.m.28 views

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks

Large language models LLMs have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/26 12:00 a.m.12 views

CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models

Retrieval-Augmented Generation RAG enhances large language models LLMs by incorporating external knowledge, but its openness introduces vulnerabilities that can be exploited by poisoning attacks. Existing poisoning methods for RAG systems have limitations, such as poor generalization and lack of...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/26 12:00 a.m.23 views

ADA: Automated Moving Target Defense for AI Workloads Via Ephemeral Infrastructure-Native Rotation in Kubernetes

This paper introduces the Adaptive Defense Agent ADA, an innovative Automated Moving Target Defense AMTD system designed to fundamentally enhance the security posture of AI workloads. ADA operates by continuously and automatically rotating these workloads at the infrastructure level, leveraging t...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/25 12:00 a.m.9 views

ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast \& Slow Reasoning for Robust Agent Defense

LLM Agents are becoming central to intelligent systems. However, their deployment raises serious safety concerns. Existing defenses largely rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user inputs or unsafe agent behaviors - creating a significant...

7.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/24 12:00 a.m.9 views

$PD^3F$: a Pluggable and Dynamic DoS-Defense Framework against Resource Consumption Attacks Targeting Large Language Models

Large Language Models LLMs, due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes, as demonstrated by denial-of-service DoS attacks designed for LLMs. However, existing works lack mitigati...

6.9AI score
SaveExploits0
Schneier on Security
Schneier on Security
added 2025/05/23 11:02 a.m.15 views

Signal Blocks Windows Recall

This article gives a good rundown of the security risks of Windows Recall, and the repurposed copyright protection took that Signal used to block the AI feature from scraping Signal data...

7.3AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2025/05/23 10:36 a.m.19 views

CVE-2024-20508

A vulnerability in Cisco Unified Threat Defense UTD Snort Intrusion Prevention System IPS Engine for Cisco IOS XE Software could allow an unauthenticated, remote attacker to bypass configured security policies or cause a denial of service DoS condition on an affected device. This vulnerability is...

6.5CVSS7.3AI score0.00417EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 10:03 a.m.12 views

CVE-2024-20306

A vulnerability in the Unified Threat Defense UTD configuration CLI of Cisco IOS XE Software could allow an authenticated, local attacker to execute arbitrary commands as root on the underlying host operating system. To exploit this vulnerability, an attacker must have level 15 privileges on the...

6.7CVSS7.5AI score0.00188EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 9:03 a.m.10 views

CVE-2024-20261

A vulnerability in the file policy feature that is used to inspect encrypted archive files of Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to bypass a configured file policy to block an encrypted archive file. This vulnerability exists because of a...

5.8CVSS6.7AI score0.0037EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 7:49 a.m.16 views

CVE-2024-20359

A vulnerability in a legacy capability that allowed for the preloading of VPN clients and plug-ins and that has been available in Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an authenticated, local attacker to execute arbitrary code...

6CVSS6.3AI score0.19434EPSS
SaveExploits1References1
RedhatCVE
RedhatCVE
added 2025/05/23 7:49 a.m.11 views

CVE-2024-20384

A vulnerability in the Network Service Group NSG feature of Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to bypass a configured access control list ACL and allow traffic that should be denied to flow...

5.8CVSS7.1AI score0.0045EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 6:14 a.m.10 views

CVE-2024-20382

A vulnerability in the VPN web client services feature of Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to conduct a cross-site scripting XSS attack against a browser that is accessing an affected...

6.1CVSS6.1AI score0.00389EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 6:14 a.m.15 views

CVE-2024-20485

A vulnerability in the VPN web server of Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an authenticated, local attacker to execute arbitrary code with root-level privileges. Administrator-level privileges are required to exploit this...

6.7CVSS7.5AI score0.00185EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 6:14 a.m.10 views

CVE-2024-20431

A vulnerability in the geolocation access control feature of Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to bypass an access control policy. This vulnerability is due to improper assignment of geolocation data. An attacker could exploit this...

5.8CVSS5.8AI score0.00395EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 5:40 a.m.11 views

CVE-2023-0524

As part of our Security Development Lifecycle, a potential privilege escalation issue was identified internally. This could allow a malicious actor with sufficient permissions to modify environment variables and abuse an impacted plugin in order to escalate privileges. We have resolved the issue...

8.8CVSS7.5AI score0.00639EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 4:53 a.m.10 views

CVE-2023-20226

A vulnerability in Application Quality of Experience AppQoE and Unified Threat Defense UTD on Cisco IOS XE Software could allow an unauthenticated, remote attacker to cause an affected device to reload unexpectedly, resulting in a denial of service DoS condition. This vulnerability is due to the...

8.6CVSS7.2AI score0.00705EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 3:27 a.m.12 views

CVE-2023-26237

An issue was discovered in WatchGuard EPDR 8.0.21.0002. It is possible to bypass the defensive capabilities by adding a registry key as SYSTEM...

6.7CVSS6.8AI score0.0017EPSS
SaveExploits0References1
Rows per page
Query Builder