Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detection

According to the Open Web Application Security Project OWASP, Cross-Site Scripting XSS is a critical security vulnerability. Despite decades of research, XSS remains among the top 10 security vulnerabilities. Researchers have proposed various techniques to protect systems from XSS attacks, with...

GenPTW: In-Generation Image Watermarking for Provenance Tracing and Tamper Localization

The rapid development of generative image models has brought tremendous opportunities to AI-generated content AIGC creation, while also introducing critical challenges in ensuring content authenticity and copyright ownership. Existing image watermarking methods, though partially effective, often...

Prefill-Based Jailbreak: a Novel Approach of Bypassing LLM Safety Boundary

Large Language Models LLMs are designed to generate helpful and safe content. However, adversarial attacks, commonly referred to as jailbreak, can bypass their safety protocols, prompting LLMs to generate harmful content or reveal sensitive data. Consequently, investigating jailbreak methodologie...

Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report

As transformer-based large language models LLMs increasingly permeate society, they have revolutionized domains such as software engineering, creative writing, and digital arts. However, their adoption in cybersecurity remains limited due to challenges like scarcity of specialized training data a...

From Paper Trails to Trust on Tracks: Adding Public Transparency to Railways Via Zk-SNARKs

Railways provide a critical service and operate under strict regulatory frameworks for implementing changes or upgrades. Despite their impact on the public, these frameworks do not define means or mechanisms for transparency towards the public, leading to reduced trust and complex tracking...

Phishing URL Detection Using Bi-LSTM

Phishing attacks threaten online users, often leading to data breaches, financial losses, and identity theft. Traditional phishing detection systems struggle with high false positive rates and are usually limited by the types of attacks they can identify. This paper proposes a deep learning-based...

SAGE: a Generic Framework for LLM Safety Evaluation

Whitepaper called SAGE: A Generic Framework For LLM Safety Evaluation...

Cybersecurity for Autonomous Vehicles

The increasing adoption of autonomous vehicles is bringing a major shift in the automotive industry. However, as these vehicles become more connected, cybersecurity threats have emerged as a serious concern. Protecting the security and integrity of autonomous systems is essential to prevent...

Inception: Jailbreak the Memory Mechanism of Text-To-Image Generation Systems

Currently, the memory mechanism has been widely and successfully exploited in online text-to-image T2I generation systems e.g., DALL E 3 for alleviating the growing tokenization burden and capturing key information in multi-turn interactions. Despite its practicality, its security analyses have...

DeeCLIP: a Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images

This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable of creating highly photorealistic images, existing detection methods often struggle to generalize across different...

The Dark Side of Digital Twins: Adversarial Attacks on AI-Driven Water Forecasting

Digital twins DTs are improving water distribution systems by using real-time data, analytics, and prediction models to optimize operations. This paper presents a DT platform designed for a Spanish water supply network, utilizing Long Short-Term Memory LSTM networks to predict water consumption...

Fast and Robust Speckle Pattern Authentication by Scale Invariant Feature Transform Algorithm in Physical Unclonable Functions

Nowadays, due to the growing phenomenon of forgery in many fields, the interest in developing new anti-counterfeiting device and cryptography keys, based on the Physical Unclonable Functions PUFs paradigm, is widely increased. PUFs are physical hardware with an intrinsic, irreproducible disorder...

Trusted Compute Units: a Framework for Chained Verifiable Computations

Blockchain and distributed ledger technologies DLTs facilitate decentralized computations across trust boundaries. However, ensuring complex computations with low gas fees and confidentiality remains challenging. Recent advances in Confidential Computing -- leveraging hardware-based Trusted...

SoK: a Survey of Mixing Techniques and Mixers for Cryptocurrencies

Blockchain technologies have overturned the digital finance industry by introducing a decentralized pseudonymous means of monetary transfer. The pseudonymous nature introduced privacy concerns, enabling various deanonymization techniques, which in turn spurred development of stronger...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

Hybrid Privacy Policy-Code Consistency Check Using Knowledge Graphs and LLMs

The increasing concern in user privacy misuse has accelerated research into checking consistencies between smartphone apps' declared privacy policies and their actual behaviors. Recent advances in Large Language Models LLMs have introduced promising techniques for semantic comparison, but these...

SILENT: a New Lens on Statistics in Software Timing Side Channels

Cryptographic research takes software timing side channels seriously. Approaches to mitigate them include constant-time coding and techniques to enforce such practices. However, recent attacks like Meltdown 42, Spectre 37, and Hertzbleed 70 have challenged our understanding of what it means for...

Metadata-Private Messaging without Coordination

For those seeking end-to-end private communication free from pervasive metadata tracking and censorship, the Tor network has been the de-facto choice in practice, despite its susceptibility to traffic analysis attacks. Recently, numerous metadata-private messaging proposals have emerged with the...

On the Prevalence and Usage of Commit Signing on GitHub: a Longitudinal and Cross-Domain Study

GitHub is one of the most widely used public code development platform. However, the code hosted publicly on the platform is vulnerable to commit spoofing that allows an adversary to introduce malicious code or commits into the repository by spoofing the commit metadata to indicate that the code...

ChipletQuake: On-Die Digital Impedance Sensing for Chiplet and Interposer Verification

Whitepaper called ChipletQuake: On-Die Digital Impedance Sensing For Chiplet And Interposer Verification...

Provably Secure Public-Key Steganography Based on Admissible Encoding

The technique of hiding secret messages within seemingly harmless covertext to evade examination by censors with rigorous security proofs is known as provably secure steganography PSS. PSS evolves from symmetric key steganography to public-key steganography, functioning without the requirement of...

SAGA: a Security Architecture for Governing AI Agentic Systems

Large Language Model LLM-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to maintain comprehensive control over their agents, mitigating...

Rational Points and Zeta Functions of Humbert Surfaces with Square Discriminant

Whitepaper called Rational Points And Zeta Functions Of Humbert Surfaces With Square Discriminant...

Comparative Analysis of AI-Driven Security Approaches in DevSecOps: Challenges, Solutions, and Future Directions

The integration of security within DevOps, known as DevSecOps, has gained traction in modern software development to address security vulnerabilities while maintaining agility. Artificial Intelligence AI and Machine Learning ML have been increasingly leveraged to enhance security automation, thre...

JailbreaksOverTime: Detecting Jailbreak Attacks under Distribution Shift

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback RLHF 32, language models remain vulnerable to jailbreak attacks that bypass safety guardrails. Universal jailbreaks - prefixes that can circumvent alignment fo...

Evaluating Organization Security: User Stories of European Union NIS2 Directive

The NIS2 directive requires EU Member States to ensure a consistently high level of cybersecurity by setting risk-management measures for essential and important entities. Evaluations are necessary to assess whether the required security level is met. This involves understanding the needs and goa...

FCGHunter: Towards Evaluating Robustness of Graph-Based Android Malware Detection

Graph-based detection methods leveraging Function Call Graphs FCGs have shown promise for Android malware detection AMD due to their semantic insights. However, the deployment of malware detectors in dynamic and hostile environments raises significant concerns about their robustness. While recent...

Detecting Speculative Data Flow Vulnerabilities Using Weakest Precondition Reasoning

Speculative execution is a hardware optimisation technique where a processor, while waiting on the completion of a computation required for an instruction, continues to execute later instructions based on a predicted value of the pending computation. It came to the forefront of security research ...

GTSD: Generative Text Steganography Based on Diffusion Model

With the rapid development of deep learning, existing generative text steganography methods based on autoregressive models have achieved success. However, these autoregressive steganography approaches have certain limitations. Firstly, existing methods require encoding candidate words according t...

Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems

Whitepaper called Differentially Private Quasi-Concave Optimization: Bypassing The Lower Bound And Application To Geometric Problems...

A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection

Various deep learning DL methods have recently been utilized to detect software vulnerabilities. Real-world software vulnerability datasets are rare and hard to acquire, as there is no simple metric for classifying vulnerability. Such datasets are heavily imbalanced, and none of the current...

SONNI: Secure Oblivious Neural Network Inference

In the standard privacy-preserving Machine learning as-a-service MLaaS model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It has become more and more common for the computation to be...

Redefining Hybrid Blockchains: a Balanced Architecture

Blockchain technology has completely revolutionized the field of decentralized finance with the emergence of a variety of cryptocurrencies and digital assets. However, widespread adoption of this technology by governments and enterprises has been limited by concerns regarding the technology's...

Security Vulnerabilities in Quantum Cloud Systems: a Survey on Emerging Threats

Quantum computing is becoming increasingly widespread due to the potential and capabilities to solve complex problems beyond the scope of classical computers. As Quantum Cloud services are adopted by businesses and research groups, they allow for greater progress and application in many fields...

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Large language models LLMs have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite these impressive achievements in mathematics and coding, the reasoning abilities of LLMs in domains requiring cryptograph...

T2VShield: Model-Agnostic Jailbreak Defense for Text-To-Video Models

The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of...

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

The challenge of ensuring Large Language Models LLMs align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against su...

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Large language models LLMs have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those who control the models. To understand how this "censorship...

The Dark Side of the Web: Towards Understanding Various Data Sources in Cyber Threat Intelligence

Cyber threats have become increasingly prevalent and sophisticated. Prior work has extracted actionable cyber threat intelligence CTI, such as indicators of compromise, tactics, techniques, and procedures TTPs, or threat feeds from various sources: open source data e.g., social networks, internal...

NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation

Large Language Models LLM are typically trained on vast amounts of data from various sources. Even when designed modularly e.g., Mixture-of-Experts, LLMs can leak privacy on their sources. Conversely, training such models in isolation arguably prohibits generalization. To this end, we propose a...

Quantum Lifting for Invertible Permutations and Ideal Ciphers

In this work, we derive the first lifting theorems for establishing security in the quantum random permutation and ideal cipher models. These theorems relate the success probability of an arbitrary quantum adversary to that of a classical algorithm making only a small number of classical queries...

Performance of Machine Learning Classifiers for Anomaly Detection in Cyber Security Applications

This work empirically evaluates machine learning models on two imbalanced public datasets KDDCUP99 and Credit Card Fraud 2013. The method includes data preparation, model training, and evaluation, using an 80/20 train/test split. Models tested include eXtreme Gradient Boosting XGB, Multi Layer...

A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection

Phishing attacks represent an increasingly sophisticated and pervasive threat to individuals and organizations, causing significant financial losses, identity theft, and severe damage to institutional reputations. Existing phishing detection methods often struggle to simultaneously achieve high...

LightDSA: a Python-Based Hybrid Digital Signature Library and Performance Analysis of RSA, DSA, ECDSA and EdDSA in Variable Configurations, Elliptic Curve Forms and Curves

Digital signature algorithms DSAs are fundamental to cryptographic security, ensuring data integrity and authentication. While RSA, DSA, ECDSA, and EdDSA are widely used, their performance varies significantly depending on key sizes, hash functions, and elliptic curve configurations. In this pape...

DeSIA: Attribute Inference Attacks against Limited Fixed Aggregate Statistics

Empirical inference attacks are a popular approach for evaluating the privacy risk of data release mechanisms in practice. While an active attack literature exists to evaluate machine learning models or synthetic data release, we currently lack comparable methods for fixed aggregate statistics, i...

issabel-pbx 4.0.0-6 Cross Site Request Forgery

issabel-pbx version 4.0.0-6 proof of concept cross site request forgery exploit that creates a new user...

ThreMoLIA: Threat Modeling of Large Language Model-Integrated Applications

Large Language Models LLMs are currently being integrated into industrial software applications to help users perform more complex tasks in less time. However, these LLM-Integrated Applications LIA expand the attack surface and introduce new kinds of threats. Threat modeling is commonly used to...

TSCL:Multi-Party Loss Balancing Scheme for Deep Learning Image Steganography Based on Curriculum Learning

For deep learning-based image steganography frameworks, in order to ensure the invisibility and recoverability of the information embedding, the loss function usually contains several losses such as embedding loss, recovery loss and steganalysis loss. In previous research works, fixed loss weight...

LLMpatronous: Harnessing the Power of LLMs for Vulnerability Detection

Despite the transformative impact of Artificial Intelligence AI across various sectors, cyber security continues to rely on traditional static and dynamic analysis tools, hampered by high false positive rates and superficial code comprehension. While generative AI offers promising automation...

ECG Identity Authentication in Open-Set with Multi-Model Pretraining and Self-Constraint Center and Irrelevant Sample Repulsion Learning

Electrocardiogram ECG signal exhibits inherent uniqueness, making it a promising biometric modality for identity authentication. As a result, ECG authentication has gained increasing attention in recent years. However, most existing methods focus primarily on improving authentication accuracy...