LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

Empirical Quantification of Spurious Correlations in Malware Detection

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep...

GenBreak: Red Teaming Text-To-Image Generators Using Large Language Models

Text-to-image T2I models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation...

AI-Based Software Vulnerability Detection: a Systematic Literature Review

Software vulnerabilities in source code pose serious cybersecurity risks, prompting a shift from traditional detection methods e.g., static analysis, rule-based matching to AI-driven approaches. This study presents a systematic review of software vulnerability detection SVD research from 2018 to...

DiffUMI: Training-Free Universal Model Inversion Via Unconditional Diffusion for Face Recognition

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which are traditionally viewed as privacy-preserving. However, model inversion...

Digital Privacy Everywhere

The increasing proliferation of digital and mobile devices equipped with cameras, microphones, GPS, and other privacy invasive components has raised significant concerns for businesses operating in sensitive or policy restricted environments. Current solutions rely on passive enforcement, such as...

Securing Open RAN: a Survey of Cryptographic Challenges and Emerging Solutions for 5G

The advent of Open Radio Access Networks O-RAN introduces modularity and flexibility into 5G deployments but also surfaces novel security challenges across disaggregated interfaces. This literature review synthesizes recent research across thirteen academic and industry sources, examining...

The Security Overview and Analysis of 3GPP 5G MAC CE

To more effectively control and allocate network resources, MAC CE has been introduced into the network protocol, which is a type of control signaling located in the MAC layer. Since MAC CE lacks encryption and integrity protection mechanisms provided by PDCP, the control signaling carried by MAC...

Generate-Then-Verify: Reconstructing Data from Limited Published Statistics

Whitepaper called Generate-Then-Verify: Reconstructing Data From Limited Published Statistics...

The Rabin Cryptosystem over Number Fields

We extend Rabin's cryptosystem to general number fields. We show that decryption of a random plaintext is as hard as the integer factorisation problem, provided the modulus in our scheme has been chosen carefully. We investigate the performance of our new cryptosystem in comparison with the...

Covert Entanglement Generation over Bosonic Channels

Whitepaper called Covert Entanglement Generation Over Bosonic Channels...

BF-Max: an Efficient Bit Flipping Decoder with Predictable Decoding Failure Rate

The Bit-Flipping BF decoder, thanks to its very low computational complexity, is widely employed in post-quantum cryptographic schemes based on Moderate Density Parity Check codes in which, ultimately, decryption boils down to syndrome decoding. In such a setting, for security concerns, one must...

Devil'S Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols

Graph neural networks GNNs have achieved significant success in graph representation learning and have been applied to various domains. However, many real-world graphs contain sensitive personal information, such as user profiles in social networks, raising serious privacy concerns when graph...

Epass: Efficient and Privacy-Preserving Asynchronous Payment on Blockchain

Whitepaper called Epass: Efficient And Privacy-Preserving Asynchronous Payment On Blockchain...

On the Impossibility of a Perfect Hypervisor

We establish a fundamental impossibility result for a perfect hypervisor', one that 1 preserves every observable behavior of any program exactly as on bare metal and 2 adds zero timing or resource overhead. Within this model we prove two theorems. 1 Indetectability Theorem. If such a hypervisor...

Physical Layer-Based Device Fingerprinting for Wireless Security: from Theory to Practice

The identification of the devices from which a message is received is part of security mechanisms to ensure authentication in wireless communications. Conventional authentication approaches are cryptography-based, which, however, are usually computationally expensive and not adequate in the...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

The Everyday Security of Living with Conflict

When cyber' is used as a prefix, attention is typically drawn to the technological and spectacular aspects of war and conflict -- and, by extension, security. We offer a different approach to engaging with and understanding security in such contexts, by foregrounding the everyday -- mundane --...

Expert-In-The-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection

As cyber threats become more sophisticated, rapid and accurate vulnerability detection is essential for maintaining secure systems. This study explores the use of Large Language Models LLMs in software vulnerability assessment by simulating the identification of Python code with known Common...

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-based, logit-based, and probe analysis to determine to what extent supposedly...

Unconditionally Secure Wireless-Wired Ground-Satellite-Ground Communication Networks Utilizing Classical and Quantum Noise

In this paper, we introduce the Kirchhoff-Law-Johnson-Noise KLJN as an approach to securing satellite communications. KLJN has the potential to revolutionize satellite communication security through its combination of simplicity, cost-effectiveness, and resilience with unconditional security...

AURA: a Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat Attribution

Effective attribution of Advanced Persistent Threats APTs increasingly hinges on the ability to correlate behavioral patterns and reason over complex, varied threat intelligence artifacts. We present AURA Attribution Using Retrieval-Augmented Agents, a multi-agent, knowledge-enhanced framework fo...

Symbolic Generation and Modular Embedding of High-Quality Abc-Triples

We present a symbolic identity for generating integer triples $a, b, c$ satisfying $a + b = c$, inspired by structural features of the \emphabc conjecture. The construction uses powers of $2$ and $3$ in combination with modular inversion in $\mathbbZ/3^p\mathbbZ$, leading to a parametric identity...

Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture

Generative Artificial Intelligence GenAI presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent systems due to increased interaction complexity. This paper...

ContextBuddy: AI-Enhanced Contextual Insights for Security Alert Investigation (Applied to Intrusion Detection)

Modern Security Operations Centres SOCs integrate diverse tools, such as SIEM, IDS, and XDR systems, offering rich contextual data, including alert enrichments, flow features, and similar case histories. Yet, analysts must still manually determine which of these contextual cues are most relevant...

Safeguarding Multimodal Knowledge Copyright in the RAG-As-A-Service Environment

As Retrieval-Augmented Generation RAG evolves into service-oriented platforms Rag-as-a-Service with shared knowledge bases, protecting the copyright of contributed data becomes essential. Existing watermarking methods in RAG focus solely on textual knowledge, leaving image knowledge unprotected. ...

WordPress Celestial Aura Theme 2.2 Shell Upload

WordPress Celestial Aura Theme versions 2.2 and below suffer from a remote shell upload vulnerability...

Navigating Cookie Consent Violations across the Globe

Online services provide users with cookie banners to accept/reject the cookies placed on their web browsers. Despite the increased adoption of cookie banners, little has been done to ensure that cookie consent is compliant with privacy laws around the globe. Prior studies have found that cookies...

Do Concept Replacement Techniques Really Erase Unacceptable Concepts?

Generative models, particularly diffusion-based text-to-image T2I models, have demonstrated astounding success. However, aligning them to avoid generating content with unacceptable concepts e.g., offensive or copyrighted content, or celebrity likenesses remains a significant challenge. Concept...

SoK: Machine Unlearning for Large Language Models

Large language model LLM unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been proposed, including Gradient Ascent, model editing, and...

Quantifying Mix Network Privacy Erosion with Generative Models

Modern mix networks improve over Tor and provide stronger privacy guarantees by robustly obfuscating metadata. As long as a message is routed through at least one honest mixnode, the privacy of the users involved is safeguarded. However, the complexity of the mixing mechanisms makes it difficult ...

Evaluation Empirique De La Sécurisation Et De L'Alignement De ChatGPT Et Gemini: Analyse Comparative Des Vulnérabilités Par Expérimentations De Jailbreaks

Large Language models LLMs are transforming digital usage, particularly in text generation, image creation, information retrieval and code development. ChatGPT, launched by OpenAI in November 2022, quickly became a reference, prompting the emergence of competitors such as Google's Gemini. However...

DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt

Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...

GPS Spoofing Attacks on AI-Based Navigation Systems with Obstacle Avoidance in UAV

Recently, approaches using Deep Reinforcement Learning DRL have been proposed to solve UAV navigation systems in complex and unknown environments. However, despite extensive research and attention, systematic studies on various security aspects have not yet been conducted. Therefore, in this pape...

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings

Federated learning FL enables collaborative model training among multiple clients without the need to expose raw data. Its ability to safeguard privacy, at the heart of FL, has recently been a hot-button debate topic. To elaborate, several studies have introduced a type of attacks known as gradie...

Apple iMessage Zero-Click Key Theft / Remote Code Execution

This is a strategic public disclosure of a zero-click iMessage exploit chain that was discovered live on iOS 18.2 and remained unpatched through iOS 18.4. It enabled Secure Enclave key theft, wormable remote code execution, and undetectable crypto wallet exfiltration. Despite responsible...

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing

Diffusion models DMs have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright infringement. Concept erasing finetunes weights to unlearn...

TimeWak: Temporal Chained-Hashing Watermark for Time Series Data

Synthetic time series generated by diffusion models enable sharing privacy-sensitive datasets, such as patients' functional MRI records. Key criteria for synthetic data include high data utility and traceability to verify the data source. Recent watermarking methods embed in homogeneous latent...

ZTaint-Havoc: from Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference

Fuzzing is a widely used technique for discovering software vulnerabilities, but identifying hot bytes that influence program behavior remains challenging. Traditional taint analysis can track such bytes white-box, but suffers from scalability issue. Fuzzing-Driven Taint Inference FTI offers a...

One Patch to Rule Them All: Transforming Static Patches into Dynamic Attacks in the Physical World

Numerous methods have been proposed to generate physical adversarial patches PAPs against real-world machine learning systems. However, each existing PAP typically supports only a single, fixed attack goal, and switching to a different objective requires re-generating and re-deploying a new PAP...

Your Agent Can Defend Itself against Backdoor Attacks

Despite their growing adoption across domains, large language model LLM-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific...

Mono: Is Your "Clean" Vulnerability Dataset Really Solvable? Exposing and Trapping Undecidable Patches and Beyond

The quantity and quality of vulnerability datasets are essential for developing deep learning solutions to vulnerability-related tasks. Due to the limited availability of vulnerabilities, a common approach to building such datasets is analyzing security patches in source code. However, existing...

Lightweight and High-Throughput Secure Logging for Internet of Things and Cold Cloud Continuum

The growing deployment of resource-limited Internet of Things IoT devices and their expanding attack surfaces demand efficient and scalable security mechanisms. System logs are vital for the trust and auditability of IoT, and offloading their maintenance to a Cold Storage-as-a-Service Cold-STaaS...

On the Ethics of Using LLMs for Offensive Security

Large Language Models LLMs have rapidly evolved over the past few years and are currently evaluated for their efficacy within the domain of offensive cyber-security. While initial forays showcase the potential of LLMs to enhance security research, they also raise critical ethical concerns regardi...

Adversarial Text Generation with Dynamic Contextual Perturbation

Adversarial attacks on Natural Language Processing NLP models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically focus on word-level or local text segment alterations,...

Secure Data Access in Cloud Environments Using Quantum Cryptography

Cloud computing has made storing and accessing data easier but keeping it secure is a big challenge nowadays. Traditional methods of ensuring data may not be strong enough in the future when powerful quantum computers become available. To solve this problem, this study uses quantum cryptography t...

What Is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?

While location trajectories offer valuable insights, they also reveal sensitive personal information. Differential Privacy DP offers formal protection, but achieving a favourable utility-privacy trade-off remains challenging. Recent works explore deep learning-based generative models to produce...

SmartAttack: Air-Gap Attack Via Smartwatches

Air-gapped systems are considered highly secure against data leaks due to their physical isolation from external networks. Despite this protection, ultrasonic communication has been demonstrated as an effective method for exfiltrating data from such systems. While smartphones have been extensivel...

ABC-FHE : a Resource-Efficient Accelerator Enabling Bootstrappable Parameters for Client-Side Fully Homomorphic Encryption

As the demand for privacy-preserving computation continues to grow, fully homomorphic encryption FHE-which enables continuous computation on encrypted data-has become a critical solution. However, its adoption is hindered by significant computational overhead, requiring 10000-fold more computatio...

Striking Back at Cobalt: Using Network Traffic Metadata to Detect Cobalt Strike Masquerading Command and Control Channels

Off-the-shelf software for Command and Control is often used by attackers and legitimate pentesters looking for discretion. Among other functionalities, these tools facilitate the customization of their network traffic so it can mimic popular websites, thereby increasing their secrecy. Cobalt...