Secure Retrieval-Augmented Generation against Poisoning Attacks

Large language models LLMs have transformed natural language processing NLP, enabling applications from content generation to decision support. Retrieval-Augmented Generation RAG improves LLMs by incorporating external knowledge but also introduces security risks, particularly from data poisoning...

RESCUE: Retrieval Augmented Secure Code Generation

Despite recent advances, Large Language Models LLMs still generate vulnerable code. Retrieval-Augmented Generation RAG has the potential to enhance LLMs for secure code generation by incorporating external security knowledge. However, the conventional RAG design struggles with the noise of raw...

Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models

Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value KV cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection MTI, a modular framework that systematically perturbs cached key...

MalCVE: Malware Detection and CVE Association Using Large Language Models

Malicious software attacks are having an increasingly significant economic impact. Commercial malware detection software can be costly, and tools that attribute malware to the specific software vulnerabilities it exploits are largely lacking. Understanding the connection between malware and the...

CTIArena: Benchmarking LLM Knowledge and Reasoning across Heterogeneous Cyber Threat Intelligence

Cyber threat intelligence CTI is central to modern cybersecurity, providing critical insights for detecting and mitigating evolving threats. With the natural language understanding and reasoning capabilities of large language models LLMs, there is increasing interest in applying them to CTI, whic...

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...

Leveraging Large Language Models for Cybersecurity Risk Assessment -- a Case from Forestry Cyber-Physical Systems

In safety-critical software systems, cybersecurity activities become essential, with risk assessment being one of the most critical. In many software teams, cybersecurity experts are either entirely absent or represented by only a small number of specialists. As a result, the workload for these...

EUVD-2025-24397

Malicious code in bioql PyPI...

Automated Vulnerability Validation and Verification: A Large Language Model Approach

Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in security practices, the lack of high-quality datasets capturing diverse exploit behavior limits effective vulnerability assessment and mitigation. This...

STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation

In modern automotive development, security testing is critical for safeguarding systems against increasingly advanced threats. Attack trees are widely used to systematically represent potential attack vectors, but generating comprehensive test cases from these trees remains a labor-intensive,...

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Retrieval-Augmented Generation RAG is an emerging approach in natural language processing that combines large language models LLMs with external document retrieval to produce more accurate and grounded responses. While RAG has shown strong potential in reducing hallucinations and improving factua...

AI Agentic Vulnerability Injection and Transformation with Optimized Reasoning

The increasing complexity of software systems and the sophistication of cyber-attacks have underscored the critical need for effective automated vulnerability detection and repair systems. Traditional methods, such as static program analysis, face significant challenges related to scalability,...

graph-rag-poc

Graph RAG Pipeline - Proof of Concept A locally-executable Gr...

Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models

Large Language Models LLMs remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including 1 adaptation to counter emerging attack strategies without costly...

Intel AI for Enterprise Retrieval-augmented Generation Search Path Uncontrolled Vulnerability

Intel AI for Enterprise Retrieval-augmented Generation is a technology framework for enhancing the accuracy and relevance of Large Language Model LLM responses by incorporating an external knowledge base. An uncontrolled search path vulnerability exists in Intel AI for Enterprise...

CVE-2025-24923

Uncontrolled search path in some IntelR AI for Enterprise Retrieval-augmented Generation software may allow an authenticated user to potentially enable escalation of privilege via local access...

CVE-2025-24923

Uncontrolled search path in some IntelR AI for Enterprise Retrieval-augmented Generation software may allow an authenticated user to potentially enable escalation of privilege via local access...

CVE-2025-24923

Uncontrolled search path in some IntelR AI for Enterprise Retrieval-augmented Generation software may allow an authenticated user to potentially enable escalation of privilege via local access...

CVE-2025-24923

Uncontrolled search path in some IntelR AI for Enterprise Retrieval-augmented Generation software may allow an authenticated user to potentially enable escalation of privilege via local access...

Intel AI for Enterprise Retrieval-augmented Generation 代码问题漏洞

Intel AI for Enterprise Retrieval-augmented Generation is a technology framework for enhancing the accuracy and relevance of Large Language Model LLM responses by incorporating an external knowledge base. An uncontrolled search path vulnerability exists in Intel AI for Enterprise...