CEGA: a Cost-Effective Approach for Graph-Based Model Extraction and Acquisition

Graph Neural Networks GNNs have demonstrated remarkable utility across diverse applications, and their growing complexity has made Machine Learning as a Service MLaaS a viable platform for scalable deployment. However, this accessibility also exposes GNN to serious security threats, most notably...

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability

Phishing attacks remain one of the most prevalent and persistent cybersecurity threat with attackers continuously evolving and intensifying tactics to evade the general detection system. Despite significant advances in artificial intelligence and machine learning, faithfully reproducing the...

Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values

Agentic AI systems, possessing capabilities for autonomous planning and action, exhibit immense potential across diverse domains. However, their practical deployment is significantly hampered by challenges in aligning their behavior with varied human values, complex safety requirements, and...

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis

The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis SCA tools struggle to effectively detect vulnerable API usage from these libraries d...

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers

Although Foundation Models FMs, such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-world interaction. To address this, FM providers introduced tool calling-triggering a proliferation of frameworks with...

deepSURF: Detecting Memory Safety Vulnerabilities in Rust through Fuzzing LLM-Augmented Harnesses

Although Rust ensures memory safety by default, it also permits the use of unsafe code, which can introduce memory safety vulnerabilities if misused. Unfortunately, existing tools for detecting memory bugs in Rust typically exhibit limited detection capabilities, inadequately handle Rust-specific...

CVE-2025-6334

A vulnerability has been found in D-Link DIR-867 1.0 and classified as critical. This vulnerability affects the function strncpy of the component Query String Handler. The manipulation leads to stack-based buffer overflow. The attack can be initiated remotely. The exploit has been disclosed to th...

Towards Effective Complementary Security Analysis Using Large Language Models

A key challenge in security analysis is the manual evaluation of potential security weaknesses generated by static application security testing SAST tools. Numerous false positives FPs in these reports reduce the effectiveness of security analysis. We propose using Large Language Models LLMs to...

Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis Via Intermediate Representation and Language Model

Malicious PDF files have emerged as a persistent threat and become a popular attack vector in web-based attacks. While machine learning-based PDF malware classifiers have shown promise, these classifiers are often susceptible to adversarial attacks, undermining their reliability. To address this...

VulnCheck KEV: CVE-2025-34023

A path traversal vulnerability exists in the Karel IP1211 IP Phone's web management panel. The /cgi-bin/cgiServer.exx endpoint fails to properly sanitize user input to the page parameter, allowing remote authenticated attackers to access arbitrary files on the underlying system by using crafted...

Server-side Request Forgery (SSRF)

Overview Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the com.powsybl.commons.xml.XmlReader class. An attacker can access sensitive files or internal resources by submitting specially crafted XML input. Note: This is only exploitable if untrusted users...

Secure Vibe Coding: The Complete New Guide

DALL-E for coders? That's the promise behind vibe coding, a term describing the use of natural language to create software. While this ushers in a new era of AI-generated code, it introduces "silent killer" vulnerabilities: exploitable flaws that evade traditional security tools despite perfect...

Probe Before You Talk: Towards Black-Box Defense against Backdoor Unalignment for Large Language Models

Backdoor unalignment attacks against Large Language Models LLMs enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of LLMs in the real-world Large Language Model as a Service...

Privacy-Preserving LLM Interaction with Socratic Chain-Of-Thought Reasoning and Homomorphically Encrypted Vector Databases

Large language models LLMs are increasingly used as personal agents, accessing sensitive user data such as calendars, emails, and medical records. Users currently face a trade-off: They can send private records, many of which are stored in remote databases, to powerful but untrusted LLM providers...

Applications of Zero-Knowledge Proofs on Bitcoin

This paper explores how zero-knowledge proofs can enhance Bitcoin's functionality and privacy. First, we consider Proof-of-Reserve schemes: by using zk-STARKs, a custodian can prove its Bitcoin holdings are more than a predefined threshold X, without revealing addresses or actual balances. We...

Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs

The increasing demand for domain-specific and human-aligned Large Language Models LLMs has led to the widespread adoption of Supervised Fine-Tuning SFT techniques. SFT datasets often comprise valuable instruction-response pairs, making them highly valuable targets for potential extraction. This...

The vulnerability of the built-in boa server (/boafrm/formSysLog) of the TOTOLINK A3002RU router’s microprogramming software allows a intruder to cause a service failure.

The vulnerability of the built-in server boa /boafrm/formSysLog of the TOTOLINK A3002RU router’s microprogramming software is related to the issue of the operation exceeding the buffer boundaries in memory when processing the submit-url parameter. Exploiting this vulnerability allows a malicious...

DEBIAN-CVE-2022-49955

In the Linux kernel, the following vulnerability has been resolved: powerpc/rtas: Fix RTAS MSRHV handling for Cell The semi-recent changes to MSR handling when entering RTAS firmware cause crashes on IBM Cell machines. An example trace: kernel tried to execute user page 2fff01a8 - exploit attempt...

DEBIAN-CVE-2025-38047

In the Linux kernel, the following vulnerability has been resolved: x86/fred: Fix system hang during S4 resume with FRED enabled Upon a wakeup from S4, the restore kernel starts and initializes the FRED MSRs as needed from its perspective. It then loads a hibernation image, including the image...

UBUNTU-CVE-2025-38047

In the Linux kernel, the following vulnerability has been resolved: x86/fred: Fix system hang during S4 resume with FRED enabled Upon a wakeup from S4, the restore kernel starts and initializes the FRED MSRs as needed from its perspective. It then loads a hibernation image, including the image...