Bridging AI and Software Security: a Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms

Large Language Model LLM agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function Calling architecture and Model Context Protocol MCP deployme...

CAVGAN: Unifying Jailbreak and Defense of LLMs Via Generative Adversarial Attacks on Their Internal Representations

Security alignment enables the Large Language Model LLM to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM jailbreak attacks and defenses. We analyze the security protection...

HPESBCR04892 rev.1 - Certain HPE ProLiant Cray Servers Using Certain AMD EPYC Processors, AMD-SB-7029: AMD Transient Scheduler Attacks, Multiple Vulnerabilities

Potential Security Impact: Local: Disclosure of Privileged Information, Disclosure of Sensitive Information SUPPORTED SOFTWARE VERSIONS: ONLY impacted versions are listed. HPE Cray EX235a Accelerator Blade - Prior to 2.1.0 in HFP 25.2.1 HPE Cray EX235n Server - Prior to 1.5.3 in HFP 25.5.0 HPE Cr...

Efficient Unlearning with Privacy Guarantees

Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning ML models trained on them. Machine unlearning has emerged as a practical means to facilitate model forgetting of data...

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation

Large Language Models LLMs have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks, and the boundary between learning and memorization. Addressi...

Large Language Models for Network Intrusion Detection Systems: Foundations, Implementations, and Future Directions

Large Language Models LLMs have revolutionized various fields with their exceptional capabilities in understanding, processing, and generating human-like text. This paper investigates the potential of LLMs in advancing Network Intrusion Detection Systems NIDS, analyzing current challenges,...

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks

Dynamic Symbolic Execution DSE is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI systems, DSE plays a crucial role in identifying hard-to-detect bugs, especially those arising from complex network...

SoK: a Systematic Review of Context- and Behavior-Aware Adaptive Authentication in Mobile Environments

As mobile computing becomes central to digital interaction, researchers have turned their attention to adaptive authentication for its real-time, context- and behavior-aware verification capabilities. However, many implementations remain fragmented, inconsistently apply intelligent techniques, an...

Emergent Misalignment As Prompt Sensitivity: a Research Note

Betley et al. 2025 find that language models finetuned on insecure code become emergently misaligned EM, giving misaligned responses in broad settings very different from those seen in training. However, it remains unclear as to why emergent misalignment occurs. We evaluate insecure models across...

Can Large Language Models Automate the Refinement of Cellular Network Specifications?

Cellular networks serve billions of users globally, yet concerns about reliability and security persist due to weaknesses in 3GPP standards. However, traditional analysis methods, including manual inspection and automated tools, struggle with increasingly expanding cellular network specifications...

Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG

Malware Family Classification MFC aims to identify the fine-grained family e.g., GuLoader or BitRAT to which a potential malware sample belongs, in contrast to malware detection or sample classification that predicts only an Yes/No. Accurate family identification can greatly facilitate automated...

SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a secure framework designed to prevent unauthorized editing in...

We Urgently Need Privilege Management in MCP: a Measurement of API Usage in MCP Ecosystems

The Model Context Protocol MCP has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensibility and rich integrations, it also introduces a substantially expanded attack surface: any plugin can inherit broad...

The New Toolkit: LLMs, Prompts, and Basic Tool Interaction

...

The Hidden Weaknesses in AI SOC Tools that No One Talks About

If you're evaluating AI-powered SOC platforms, you've likely seen bold claims: faster triage, smarter remediation, and less noise. But under the hood, not all AI is created equal. Many solutions rely on pre-trained AI models that are hardwired for a handful of specific use cases. While that might...

The Rise of Agentic AI: Uncovering Security Risks in AI Web Agents

In our first post, we introduced the world of AI web agents - defining what they are, outlining their core capabilities, and surveying the leading frameworks that make them possible. Now, we’re shifting gears to look at the other side of the coin: the vulnerabilities and attack surfaces that aris...

PT-2025-39733

Name of the Vulnerable Software and Affected Versions llama-index-core versions through 0.12.44 Description The software has an issue in the get cache dir function due to the use of a predictable, hardcoded directory path /tmp/llama index on Linux systems without sufficient security measures. Thi...

Malicious AI Models Are Behind a New Wave of Cybercrime, Cisco Talos

Cybercriminals use malicious AI models to write malware and phishing scams Cisco Talos warns of rising threats from uncensored and custom AI tools...

TB-eye多款产品 安全漏洞

TB-eye Network recorders and TB-eye AHD recorders are both products of TB-eye Corporation of Japan.TB-eye Network recorders are a line of network recorders.TB-eye AHD recorders are a line of video recorders. A security vulnerability exists in several TB-eye products, which is caused by a buffer...

TB-eye多款产品 操作系统命令注入漏洞

TB-eye Network recorders and TB-eye AHD recorders are both products of the Japanese company TB-eye.TB-eye Network recorders are a line of network recorders.TB-eye AHD recorders are a line of video recorders. An operating system command injection vulnerability exists in several TB-eye products,...