PT-2025-32556

Name of the Vulnerable Software and Affected Versions: ModelCache for LLM versions through 0.2.0 Description: ModelCache for LLM through version 0.2.0 contains a deserialization vulnerability in the /manager/data manager.py component. This allows attackers to execute arbitrary code by supplying...

Who'S the Evil Twin? Differential Auditing for Undesired Behavior

Detecting hidden behaviors in neural networks poses a significant challenge due to minimal prior knowledge and potential adversarial obfuscation. We explore this problem by framing detection as an adversarial game between two teams: the red team trains two similar models, one trained solely on...

Mitigating Distribution Shift in Graph-Based Android Malware Classification Via Function Metadata and LLM Embeddings

Graph-based malware classifiers can achieve over 94% accuracy on standard Android datasets, yet we find they suffer accuracy drops of up to 45% when evaluated on previously unseen malware variants from the same family - a scenario where strong generalization would typically be expected. This...

Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination

Timely and effective incident response is key to managing the growing frequency of cyberattacks. However, identifying the right response actions for complex systems is a major technical challenge. A promising approach to mitigate this challenge is to use the security knowledge embedded in large...

Attack the Messages, Not the Agents: a Multi-Round Adaptive Stealthy Tampering Framework for LLM-MAS

Large language model-based multi-agent systems LLM-MAS effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct...

PhishParrot: LLM-Driven Adaptive Crawling to Unveil Cloaked Phishing Sites

Phishing attacks continue to evolve, with cloaking techniques posing a significant challenge to detection efforts. Cloaking allows attackers to display phishing sites only to specific users while presenting legitimate pages to security crawlers, rendering traditional detection systems ineffective...

PentestJudge: Judging Agent Behavior against Operational Requirements

We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model LLM-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and tool call history to determine whether a security agent's...

VWAttacker: a Systematic Security Testing Framework for Voice over WiFi User Equipments

We present VWAttacker, the first systematic testing framework for analyzing the security of Voice over WiFi VoWiFi User Equipment UE implementations. VWAttacker includes a complete VoWiFi network testbed that communicates with Commercial-Off-The-Shelf COTS UEs based on a simple interface to test...

Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection

With the rapid expansion of web-based applications and cloud services, malicious JavaScript code continues to pose significant threats to user privacy, system integrity, and enterprise security. But, detecting such threats remains challenging due to sophisticated code obfuscation techniques and...

Large Language Model-Based Framework for Explainable Cyberattack Detection in Automatic Generation Control Systems

The increasing digitization of smart grids has improved operational efficiency but also introduced new cybersecurity vulnerabilities, such as False Data Injection Attacks FDIAs targeting Automatic Generation Control AGC systems. While machine learning ML and deep learning DL models have shown...

Enhancing Jailbreak Attacks on LLMs Via Persona Prompts

Jailbreak attacks aim to exploit large language models LLMs by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM safety. Previous jailbreak approaches have mainly focused on dire...

LLM4MEA: Data-Free Model Extraction Attacks on Sequential Recommenders Via Large Language Models

Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks MEAs. MEAs collect responses from recommender systems to replicate their functionality, enabling unauthorized deployments and posing critical privacy and security risks. Black-box...

Chaindesk Cross Site Scripting

Chaindesk, a web application for constructing AI Agents, is vulnerable to a persistent cross site scripting vulnerability in its agent chat component. An attacker can achieve arbitrary client-side script execution by crafting an AI agent whose system prompt instructs the underlying Large Language...

FaultLine: Automated Proof-Of-Vulnerability Generation Using LLM Agents

Despite the critical threat posed by software security vulnerabilities, reports are often incomplete, lacking the proof-of-vulnerability PoV tests needed to validate fixes and prevent regressions. These tests are crucial not only for ensuring patches work, but also for helping developers understa...

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

Large Language Models LLMs deployed in enterprise settings e.g., as Microsoft 365 Copilot face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data. In this paper, we present a...

CERT-UA Discovers LAMEHUG Malware Linked to APT28, Using LLM for Phishing Campaign

The Computer Emergency Response Team of Ukraine CERT-UA has disclosed details of a phishing campaign that's designed to deliver a malware codenamed LAMEHUG. "An obvious feature of LAMEHUG is the use of LLM large language model, used to generate commands based on their textual representation...

Perplexity AI Web Application 安全漏洞

Perplexity AI Web Application is a big data search engine application utilizing a big language model from Perplexity, Inc. in the United States. A security vulnerability exists in Perplexity AI Web Application GPT-4 version 2.51.0, which stems from mishandling of the token component and could lea...

Is AI “healthy” to use? (Lock and Code S06E14)

This week on the Lock and Code podcast … “Health” isn’t the first feature that most anyone thinks about when trying out a new technology, but a recent spate of news is forcing the issue when it comes to artificial intelligence AI. In June, The New York Times reported on a group of ChatGPT users w...

Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing

As the frequency of cyber threats increases, conventional penetration testing is failing to capture the entirety of todays complex environments. To solve this problem, we propose the Vulnerability Mitigation System VMS, a novel agent based on a Large Language Model LLM capable of performing...

LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing

We introduce the framework of LLM-Stackelberg games, a class of sequential decision-making models that integrate large language models LLMs into strategic interactions between a leader and a follower. Departing from classical Stackelberg assumptions of complete information and rational agents, ou...