SKALD: Scalable K-Anonymisation for Large Datasets

Data privacy and anonymisation are critical concerns in today's data-driven society, particularly when handling personal and sensitive user data. Regulatory frameworks worldwide recommend privacy-preserving protocols such as k-anonymisation to de-identify releases of tabular data. Available...

BadLingual: a Novel Lingual-Backdoor Attack against Large Language Models

In this paper, we present a new form of backdoor attack against Large Language Models LLMs: lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hijack the infected LLMs to generate inflammatory speech. They enable the precise...

Mitigating Backdoor Triggered and Targeted Data Poisoning Attacks in Voice Authentication Systems

Voice authentication systems remain susceptible to two major threats: backdoor triggered attacks and targeted data poisoning attacks. This dual vulnerability is critical because conventional solutions typically address each threat type separately, leaving systems exposed to adversaries who can...

Directed Greybox Fuzzing Via Large Language Model

Directed greybox fuzzing DGF focuses on efficiently reaching specific program locations or triggering particular behaviors, making it essential for tasks like vulnerability detection and crash reproduction. However, existing methods often suffer from path explosion and randomness in input mutatio...

Bridging Expertise Gaps: the Role of LLMs in Human-AI Collaboration for Cybersecurity

This study investigates whether large language models LLMs can function as intelligent collaborators to bridge expertise gaps in cybersecurity decision-making. We examine two representative tasks-phishing email detection and intrusion detection-that differ in data modality, cognitive complexity,...

USN-7478-1 corosync vulnerability

It was discovered that Corosync incorrectly handled certain large UDP packets. If encryption is disabled, or an attacker knows the encryption key, this issue could be used to cause Corosync to crash, resulting in a denial of service...

Towards a Standardized Methodology and Dataset for Evaluating LLM-Based Digital Forensic Timeline Analysis

Large language models LLMs have seen widespread adoption in many domains including digital forensics. While prior research has largely centered on case studies and examples demonstrating how LLMs can assist forensic investigations, deeper explorations remain limited, i.e., a standardized approach...

CAMEL - The First And The Best Multi-Agent Framework. Finding The Scaling Law Of Agents

🐫 CAMEL is an open-source community dedicated to finding the scaling laws of agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various type...

A Survey on Privacy Risks and Protection in Large Language Models

Although Large Language Models LLMs have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. Firs...

DEBIAN-CVE-2023-53134

In the Linux kernel, the following vulnerability has been resolved: bnxten: Avoid order-5 memory allocation for TPA data The driver needs to keep track of all the possible concurrent TPA GRO/LRO completions on the aggregation ring. On P5 chips, the maximum number of concurrent TPA is 256 and the...

SUSE CVE-2025-37761

In the Linux kernel, the following vulnerability has been resolved: drm/xe: Fix an out-of-bounds shift when invalidating TLB When the size of the range invalidated is larger than rounddownpowoftwoULONGMAX, The function macro rounduppowoftwolength will hit an out-of-bounds shift 1. Use a full TLB...

Good News for Script Kiddies? Evaluating Large Language Models for Automated Exploit Generation

Large Language Models LLMs have demonstrated remarkable capabilities in code-related tasks, raising concerns about their potential for automated exploit generation AEG. This paper presents the first systematic study on LLMs' effectiveness in AEG, evaluating both their cooperativeness and technica...

LLM Watermarking Using Mixtures and Statistical-To-Computational Gaps

Given a text, can we determine whether it was generated by a large language model LLM or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed setting. Also, in the harder open setting, where the adversar...

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures

As large language models LLMs continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and categorize the various attacks targeting LLMs, distinguishing...

DEBIAN-CVE-2025-37761

In the Linux kernel, the following vulnerability has been resolved: drm/xe: Fix an out-of-bounds shift when invalidating TLB When the size of the range invalidated is larger than rounddownpowoftwoULONGMAX, The function macro rounduppowoftwolength will hit an out-of-bounds shift 1. Use a full TLB...

Can Differentially Private Fine-Tuning LLMs Protect against Privacy Attacks?

Fine-tuning large language models LLMs has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and exposed. Although differential privacy DP offers strong...

OET: Optimization-Based Prompt Injection Evaluation Toolkit

Large Language Models LLMs have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks poses significant security risks, as adversarial inputs can...

From Texts to Shields: Convergence of Large Language Models and Cybersecurity

This report explores the convergence of large language models LLMs and cybersecurity, synthesizing interdisciplinary insights from network security, artificial intelligence, formal methods, and human-centered design. It examines emerging applications of LLMs in software and network security, 5G...

An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding

Binary code analysis plays a pivotal role in the field of software security and is widely used in tasks such as software maintenance, malware detection, software vulnerability discovery, patch analysis, etc. However, unlike source code, reverse engineers face significant challenges in understandi...

vLLM 安全漏洞

vLLM is a vLLM open source high throughput and memory efficient reasoning and service engine for LLM. A security vulnerability exists in vLLM versions prior to 0.5.2 through 0.8.5, which stems from ZeroMQ could lead to denial of service and data exposure...