Improving LLM Outputs against Jailbreak Attacks with Expert Model Integration

Using LLMs in a production environment presents security challenges that include vulnerabilities to jailbreaks and prompt injections, which can result in harmful outputs for humans or the enterprise. The challenge is amplified when working within a specific domain, as topics generally accepted fo...

WASP: Benchmarking Web Agent Security against Prompt Injection Attacks

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is exacerbated by the agent's ability to take action on their...

AutoRAN: Weak-To-Strong Jailbreaking of Large Reasoning Models

This paper presents AutoRAN, the first automated, weak-to-strong jailbreak attack framework targeting large reasoning models LRMs. At its core, AutoRAN leverages a weak, less-aligned reasoning model to simulate the target model's high-level reasoning structures, generates narrative prompts, and...

ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks

The integration of large language models LLMs into a wide range of applications has highlighted the critical role of well-crafted system prompts, which require extensive testing and domain expertise. These prompts enhance task performance but may also encode sensitive information and filtering...

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

The integration of large language models LLMs into cyber security applications presents significant opportunities, such as enhancing threat analysis and malware detection, but can also introduce critical risks and safety concerns, including personal data leakage and automated generation of new...

DataSentinel: a Game-Theoretic Detection of Prompt Injection Attacks

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where an attacker injects prompts into their inputs to induce attacker-desired outputs. A detection method aims to determine whether a given input is contaminated by an injected prompt. However, existing detection...

FreeBSD : vscode -- security feature bypass vulnerability (6f10b49d-07b1-4be4-8abf-edf880b16ad2)

The version of FreeBSD installed on the remote host is prior to tested version. It is, therefore, affected by a vulnerability as referenced in the 6f10b49d-07b1-4be4-8abf-edf880b16ad2 advisory. VSCode developers report: A security feature bypass vulnerability exists in VS Code 1.100.0 and earlier...

GenAI Security: Outsmarting the Bots with a Proactive Testing Framework

The increasing sophistication and integration of Generative AI GenAI models into diverse applications introduce new security challenges that traditional methods struggle to address. This research explores the critical need for proactive security measures to mitigate the risks associated with...

PCMan FTP Server PROMPT Command Handler Buffer Overflow Vulnerability

PCMan FTP Server is PCMan open source set of FTP server software. PCMan FTP Server suffers from a buffer overflow vulnerability that originates from the PROMPT command handler failing to properly validate the length of input data, which can be exploited by an attacker to cause a denial of service...

Red Teaming the Mind of the Machine: a Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Large Language Models LLMs are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation o...

vscode -- security feature bypass vulnerability

VSCode developers report: A security feature bypass vulnerability exists in VS Code 1.100.0 and earlier versions where a maliciously crafted URL could be considered trusted when it should not have due to how VS Code handled glob patterns in the trusted domains feature. When paired with the fetch...

LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-Induced Risks and Vulnerabilities

The growing adoption of Large Language Models LLMs has influenced the development of their lighter counterparts-Small Language Models SLMs-to enable on-device deployment across smartphones and edge devices. These SLMs offer enhanced privacy, reduced latency, server-free functionality, and improve...

TokenProber: Jailbreaking Text-To-Image Models Via Fine-Grained Word Impact Analysis

Text-to-image T2I models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work NSFW content, such as pornography, violence, political content, and discrimination. To mitigate the risk of generating NSFW...

System Prompt Poisoning: Persistent Attacks on Large Language Models beyond User Injection

Large language models LLMs have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through simple prompts. However, as LLMs become more integrated in...

Security Steerability Is All You Need

The adoption of Generative AI GenAI in various applications inevitably comes with expanding the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate these security threats in GenAI by developing...

Defending against Indirect Prompt Injection by Instruction Detection

The integration of Large Language Models LLMs with external sources is becoming increasingly common, with Retrieval-Augmented Generation RAG being a prominent example. However, this integration introduces vulnerabilities of Indirect Prompt Injection IPI attacks, where hidden instructions embedded...

CVE-2025-46826

CVE-2025-46826 affects the insa-auth authentication server (INSA Rouen). The issue is a minor Open-Redirect/secondary authentication bridge exposure that could allow third-party websites to access basic student information (name and number). It posed low risk, was not exploited, and a fix was dep...

CVE-2025-46826 insa-auth Open-Redirect on provided CAS server login endpoint

insa-auth is an authentication server for INSA Rouen. A minor issue allowed third-party websites to access the server's secondary authentication bridge, potentially revealing basic student information name and number. However, the issue posed minimal risk, was never exploited, and had limited...

python-prompt-toolkit bug fix and enhancement update

An update is available for python-prompt-toolkit. This update affects Rocky Linux 9. A Common Vulnerability Scoring System CVSS base score, which gives a detailed severity rating, is available for each vulnerability from the CVE list For detailed information on changes in this release, see the...

A Proposal for Evaluating the Operational Risk for ChatBots Based on Large Language Models

The emergence of Generative AI Gen AI and Large Language Models LLMs has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend beyond traditional cybersecurity considerations. In this work, ...