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...

Permissioned LLMs: Enforcing Access Control in Large Language Models

In enterprise settings, organizational data is segregated, siloed and carefully protected by elaborate access control frameworks. These access control structures can completely break down if an LLM fine-tuned on the siloed data serves requests, for downstream tasks, from individuals with disparat...

CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning

Privacy-Preserving Federated Learning PPFL is a decentralized machine learning approach where multiple clients train a model collaboratively. PPFL preserves privacy and security of the client's data by not exchanging it. However, ensuring that data at each client is of high quality and ready for...

Transformers in Protein: a Survey

As protein informatics advances rapidly, the demand for enhanced predictive accuracy, structural analysis, and functional understanding has intensified. Transformer models, as powerful deep learning architectures, have demonstrated unprecedented potential in addressing diverse challenges across...

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

Retrieval-Augmented Generation RAG has proven effective in mitigating hallucinations in large language models by incorporating external knowledge during inference. However, this integration introduces new security vulnerabilities, particularly to poisoning attacks. Although prior work has explore...

LLM-Driven APT Detection for 6G Wireless Networks: a Systematic Review and Taxonomy

Sixth Generation 6G wireless networks, which are expected to be deployed in the 2030s, have already created great excitement in academia and the private sector with their extremely high communication speed and low latency rates. However, despite the ultra-low latency, high throughput, and...

CVE-2024-9202

In Eclipse Dataspace Components versions 0.1.3 to 0.9.0, the Connector component filters which datasets = data offers another party can see in a requested catalog, to ensure that only authorized parties are able to view restricted offers. However, there is the possibility to request a single...

CVE-2024-42351

Galaxy is a free, open-source system for analyzing data, authoring workflows, training and education, publishing tools, managing infrastructure, and more. An attacker can potentially replace the contents of public datasets resulting in data loss or tampering. All supported branches of Galaxy and...

Safe Delta: Consistently Preserving Safety When Fine-Tuning LLMs on Diverse Datasets

Large language models LLMs have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to upload their own data for LLM customization. However,...

Privacy-Preserving AI for Encrypted Medical Imaging: a Framework for Secure Diagnosis and Learning

The rapid integration of Artificial Intelligence AI into medical diagnostics has raised pressing concerns about patient privacy, especially when sensitive imaging data must be transferred, stored, or processed. In this paper, we propose a novel framework for privacy-preserving diagnostic inferenc...

AutoRAN: Weak-To-Strong Jailbreaking of Large Reasoning Models

This paper presents AutoRAN, the first automated, weak-to-strong jailbreak attack framework targeting large reasoning models LRMs. At its core, AutoRAN leverages a weak, less-aligned reasoning model to simulate the target model's high-level reasoning structures, generates narrative prompts, and...

GenoArmory: a Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

We propose the first unified adversarial attack benchmark for Genomic Foundation Models GFMs, named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologicall...

Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

As Large Language Models LLMs are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from human feedback RLHF, they are still vulnerable to jailbreakin...

Incorrect Default Permissions

Overview apache-superset is a modern, enterprise-ready business intelligence web application. Affected versions of this package are vulnerable to Incorrect Default Permissions due to missing validations, which allow an attacker to take over ownership of dashboards, charts, or datasets. Note: This...

ABAC Lab: an Interactive Platform for Attribute-Based Access Control Policy Analysis, Tools, and Datasets

Attribute-Based Access Control ABAC provides expressiveness and flexibility, making it a compelling model for enforcing fine-grained access control policies. To facilitate the transition to ABAC, extensive research has been conducted to develop methodologies, frameworks, and tools that assist...

LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems

The increasing complexity and scale of the Internet of Things IoT have made security a critical concern. This paper presents a novel Large Language Model LLM-based framework for comprehensive threat detection and prevention in IoT environments. The system integrates lightweight LLMs fine-tuned on...

Machine Learning-Based Detection of DDoS Attacks in VANETs for Emergency Vehicle Communication

Vehicular Ad Hoc Networks VANETs play a key role in Intelligent Transportation Systems ITS, particularly in enabling real-time communication for emergency vehicles. However, Distributed Denial of Service DDoS attacks, which interfere with safety-critical communication channels, can severely impai...

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Most existing unlearnable strategies focus on preventing unauthorized users from training single-task learning STL models with personal data. Nevertheless, the paradigm has recently shifted towards multi-task data and multi-task learning MTL, targeting generalist and foundation models that can...

Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain

As Spiking Neural Networks SNNs gain traction across various applications, understanding their security vulnerabilities becomes increasingly important. In this work, we focus on the adversarial attacks, which is perhaps the most concerning threat. An adversarial attack aims at finding a subtle...

A Framework to Prevent Biometric Data Leakage in the Immersive Technologies Domain

Doubtlessly, the immersive technologies have potential to ease people's life and uplift economy, however the obvious data privacy risks cannot be ignored. For example, a participant wears a 3D headset device which detects participant's head motion to track the pose of participant's head to match...