An Algorithmic Pipeline for GDPR-Compliant Healthcare Data Anonymisation: Moving toward Standardisation

High-quality real-world data RWD is essential for healthcare but must be transformed to comply with the General Data Protection Regulation GDPR. GDPRs broad definitions of quasi-identifiers QIDs and sensitive attributes SAs complicate implementation. We aim to standardise RWD anonymisation for GD...

ARIANNA: an Automatic Design Flow for Fabric Customization and EFPGA Redaction

In the modern global Integrated Circuit IC supply chain, protecting intellectual property IP is a complex challenge, and balancing IP loss risk and added cost for theft countermeasures is hard to achieve. Using embedded configurable logic allows designers to completely hide the functionality of...

PUB-A-394726109

Analysis: Access Vector: Local Layer: Userland Root Causes: Heap Buffer Overflow SRS Categories: - Android Security SRS Category: Memory Safety Writeup: A stack trace alone with PoC app is insufficient to determine if this represents a genuine memory corruption vulnerability reachable by an...

Breaking the Gold Standard: Extracting Forgotten Data under Exact Unlearning in Large Language Models

Large language models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove the influence of specific data from trained models. Of...

Evaluating the Security Efficacy of Web Application Firewalls (WAFs)

Web Application Firewalls WAFs are now a staple in defending web-facing applications and APIs, acting as specialized filters to block malicious traffic before it ever reaches your systems. But simply deploying a WAF isn’t enough, the real challenge is knowing whether it works when it matters most...

Fooling the Watchers: Breaking AIGC Detectors Via Semantic Prompt Attacks

The rise of text-to-image T2I models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial prompt generation framework that leverages a grammar tree...

LLM Agents Should Employ Security Principles

Large Language Model LLM agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of context manipulation introduce new vulnerabilities related to...

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?

Fine-tuning large language models LLMs for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can...

Jailbreak Distillation: Renewable Safety Benchmarking

Large language models LLMs are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation JBDistill, a novel benchmark construction framework that "distills" jailbreak attacks into high-quality and easily-updatable safety...

GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance

DNA, encoding genetic instructions for almost all living organisms, fuels groundbreaking advances in genomics and synthetic biology. Recently, DNA Foundation Models have achieved success in designing synthetic functional DNA sequences, even whole genomes, but their susceptibility to jailbreaking...

Aurora: Are Android Malware Classifiers Reliable under Distribution Shift?

The performance figures of modern drift-adaptive malware classifiers appear promising, but does this translate to genuine operational reliability? The standard evaluation paradigm primarily focuses on baseline performance metrics, neglecting confidence-error alignment and operational stability...

Hunting the Ghost: Towards Automatic Mining of IoT Hidden Services

In this paper, we proposes an automatic firmware analysis tool targeting at finding hidden services that may be potentially harmful to the IoT devices. Our approach uses static analysis and symbolic execution to search and filter services that are transparent to normal users but explicit to...

Authorization Bypass

github.com/openfga/openfga is vulnerable to authorization bypass. The vulnerability is due to incorrect permission evaluation when usersets and type-bound public access overlap without proper tuple assignments, allowing attackers unauthorized resource access or actions...

The Feasibility of Topic-Based Watermarking on Academic Peer Reviews

Large language models LLMs are increasingly integrated into academic workflows, with many conferences and journals permitting their use for tasks such as language refinement and literature summarization. However, their use in peer review remains prohibited due to concerns around confidentiality...

System Prompt Extraction Attacks and Defenses in Large Language Models

The system prompt in Large Language Models LLMs plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that...

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emphComputer-Using Agents CUAs, capable of autonomously...

Phare: a Safety Probe for Large Language Models

Ensuring the safety of large language models LLMs is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to probe and evaluate LLM behavior across three critical...

Evaluating Query Efficiency and Accuracy of Transfer Learning-Based Model Extraction Attack in Federated Learning

Federated Learning FL is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property IP threats. Model extraction ME attacks pose a significant risk to Machine Learning as a Service MLaaS platforms, enabling attackers to replicate...

CVE-2024-32646

Vyper is a pythonic Smart Contract Language for the Ethereum virtual machine. In versions 0.3.10 and prior, using the slice builtin can result in a double eval vulnerability when the buffer argument is either msg.data, self.code or .code and either the start or length arguments have side-effects...

CVE-2024-33327

A cross-site scripting XSS vulnerability in the component UrlAccessibilityEvaluation.jsp of Lumisxp v15.0.x to v16.1.x allows attackers to execute arbitrary web scripts or HTML via a crafted payload injected into the contentHtml parameter...