Source Anonymity for Private Random Walk Decentralized Learning

This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data privacy is a central concern and open problem in decentralize...

Revealing Weaknesses in Text Watermarking through Self-Information Rewrite Attacks

Text watermarking aims to subtly embed statistical signals into text by controlling the Large Language Model LLM's sampling process, enabling watermark detectors to verify that the output was generated by the specified model. The robustness of these watermarking algorithms has become a key factor...

Optimizing Mouse Dynamics for User Authentication by Machine Learning: Addressing Data Sufficiency, Accuracy-Practicality Trade-Off, and Model Performance Challenges

User authentication is essential to ensure secure access to computer systems, yet traditional methods face limitations in usability, cost, and security. Mouse dynamics authentication, based on the analysis of users' natural interaction behaviors with mouse devices, offers a cost-effective,...

Real-Time Bit-Level Encryption of Full High-Definition Video without Diffusion

Despite the widespread adoption of Shannon's confusion-diffusion architecture in image encryption, the implementation of diffusion to sequentially establish inter-pixel dependencies for attaining plaintext sensitivity constrains algorithmic parallelism, while the execution of multiple rounds of...

Security of Internet of Agents: Attacks and Countermeasures

With the rise of large language and vision-language models, AI agents have evolved into autonomous, interactive systems capable of perception, reasoning, and decision-making. As they proliferate across virtual and physical domains, the Internet of Agents IoA has emerged as a key infrastructure fo...

POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models

Large language models LLMs have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite their impressive performance, LLMs are susceptible to hallucinations, which can lead to incorrect or misleading outputs...

An \Tilde{O}Ptimal Differentially Private Learner for Concept Classes with VC Dimension 1

We present the first nearly optimal differentially private PAC learner for any concept class with VC dimension 1 and Littlestone dimension $d$. Our algorithm achieves the sample complexity of $\tildeO\varepsilon,δ,α,δ\log^ d$, nearly matching the lower bound of $Ω\log^ d$ proved by Alon et al...

AI-Powered Anomaly Detection with Blockchain for Real-Time Security and Reliability in Autonomous Vehicles

Autonomous Vehicles AV proliferation brings important and pressing security and reliability issues that must be dealt with to guarantee public safety and help their widespread adoption. The contribution of the proposed research is towards achieving more secure, reliable, and trustworthy autonomou...

Practical Reasoning Interruption Attacks on Reasoning Large Language Models

Reasoning large language models RLLMs have demonstrated outstanding performance across a variety of tasks, yet they also expose numerous security vulnerabilities. Most of these vulnerabilities have centered on the generation of unsafe content. However, recent work has identified a distinct...

RuleGenie: SIEM Detection Rule Set Optimization

SIEM systems serve as a critical hub, employing rule-based logic to detect and respond to threats. Redundant or overlapping rules in SIEM systems lead to excessive false alerts, degrading analyst performance due to alert fatigue, and increase computational overhead and response latency for actual...

Sandcastles in the Storm: Revisiting the (Im)Possibility of Strong Watermarking

Watermarking AI-generated text is critical for combating misuse. Yet recent theoretical work argues that any watermark can be erased via random walk attacks that perturb text while preserving quality. However, such attacks rely on two key assumptions: 1 rapid mixing watermarks dissolve quickly...

A Contrastive Federated Semi-Supervised Learning Intrusion Detection Framework for Internet of Robotic Things

In intelligent industry, autonomous driving and other environments, the Internet of Things IoT highly integrated with robotic to form the Internet of Robotic Things IoRT. However, network intrusion to IoRT can lead to data leakage, service interruption in IoRT and even physical damage by...

ThreatLens: LLM-Guided Threat Modeling and Test Plan Generation for Hardware Security Verification

Current hardware security verification processes predominantly rely on manual threat modeling and test plan generation, which are labor-intensive, error-prone, and struggle to scale with increasing design complexity and evolving attack methodologies. To address these challenges, we propose...

DPolicy: Managing Privacy Risks across Multiple Releases with Differential Privacy

Differential Privacy DP has emerged as a robust framework for privacy-preserving data releases and has been successfully applied in high-profile cases, such as the 2020 US Census. However, in organizational settings, the use of DP remains largely confined to isolated data releases. This approach...

Centralized Trust in Decentralized Systems: Unveiling Hidden Contradictions in Blockchain and Cryptocurrency

Blockchain technology promises to democratize finance and promote social equity through decentralization, but questions remain about whether current implementations advance or hinder these goals. Through a mixed-methods study combining semi-structured interviews with 13 diverse blockchain...

Privacy-Aware Berrut Approximated Coded Computing Applied to General Distributed Learning

Coded computing is one of the techniques that can be used for privacy protection in Federated Learning. However, most of the constructions used for coded computing work only under the assumption that the computations involved are exact, generally restricted to special classes of functions, and...

Causality for Cyber-Physical Systems

We present a formal theory for analysing causality in cyber-physical systems. To this end, we extend the theory of actual causality by Halpern and Pearl to cope with the continuous nature of cyber-physical systems. Based on our theory, we develop an analysis technique that is used to uncover the...

Measuring Security in 5G and Future Networks

In today's increasingly interconnected and fast-paced digital ecosystem, mobile networks, such as 5G and future generations such as 6G, play a pivotal role and must be considered as critical infrastructures. Ensuring their security is paramount to safeguard both individual users and the industrie...

Leakage-Resilient Algebraic Manipulation Detection Codes with Optimal Parameters

Algebraic Manipulation Detection AMD codes is a cryptographic primitive that was introduced by Cramer, Dodis, Fehr, Padro and Wichs. They are keyless message authentication codes that protect messages against additive tampering by the adversary assuming that the adversary cannot "see" the codewor...

Remote Rowhammer Attack Using Adversarial Observations on Federated Learning Clients

Federated Learning FL has the potential for simultaneous global learning amongst a large number of parallel agents, enabling emerging AI such as LLMs to be trained across demographically diverse data. Central to this being efficient is the ability for FL to perform sparse gradient updates and...

LATENT: LLM-Augmented Trojan Insertion and Evaluation Framework for Analog Netlist Topologies

Analog and mixed-signal A/MS integrated circuits ICs are integral to safety-critical applications. However, the globalization and outsourcing of A/MS ICs to untrusted third-party foundries expose them to security threats, particularly analog Trojans. Unlike digital Trojans which have been...

RiM: Record, Improve and Maintain Physical Well-Being Using Federated Learning

In academic settings, the demanding environment often forces students to prioritize academic performance over their physical well-being. Moreover, privacy concerns and the inherent risk of data breaches hinder the deployment of traditional machine learning techniques for addressing these health...

Safety Analysis in the NGAC Model

We study the safety problem for the next-generation access control NGAC model. We show that under mild assumptions it is coNP-complete, and under further realistic assumptions we give an algorithm for the safety problem that significantly outperforms naive brute force search. We also show that...

Cryptanalysis of a Lattice-Based PIR Scheme for Arbitrary Database Sizes

Private Information Retrieval PIR schemes enable users to securely retrieve files from a server without disclosing the content of their queries, thereby preserving their privacy. In 2008, Melchor and Gaborit proposed a PIR scheme that achieves a balance between communication overhead and...

Representation Gaps of Rigid Planar Diagram Monoids

We define non-pivotal analogs of the Temperley-Lieb, Motzkin, and planar rook monoids, and compute bounds for the sizes of their nontrivial simple representations. From this, we assess the two types of monoids in their relative suitability for use in cryptography by comparing their representation...

Towards Quantum Resilience: Data-Driven Migration Strategy Design

The advancements in quantum computing are a threat to classical cryptographic systems. The traditional cryptographic methods that utilize factorization-based or discrete-logarithm-based algorithms, such as RSA and ECC, are some of these. This paper thoroughly investigates the vulnerabilities of...

HashKitty: Distributed Password Analysis

This article documents the HashKitty platform, a distributed solution for password analysis based on the hashcat tool, designed to improve efficiency in both offensive and defensive security operations. The main objectives of this work are to utilise and characterise the hashcat tool, to develop ...

Self-Supervised Federated GNSS Spoofing Detection with Opportunistic Data

Global navigation satellite systems GNSS are vulnerable to spoofing attacks, with adversarial signals manipulating the location or time information of receivers, potentially causing severe disruptions. The task of discerning the spoofing signals from benign ones is naturally relevant for machine...

A Taxonomy of Attacks and Defenses in Split Learning

Split Learning SL has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent research has demonstrated that SL remains vulnerable to a...

Exploring the Susceptibility to Fraud of Monetary Incentive Mechanisms for Strengthening FOSS Projects

Free and open source software FOSS is ubiquitous on modern IT systems, accelerating the speed of software engineering over the past decades. With its increasing importance and historical reliance on uncompensated contributions, questions have been raised regarding the continuous maintenance of FO...

On the Price of Differential Privacy for Spectral Clustering over Stochastic Block Models

We investigate privacy-preserving spectral clustering for community detection within stochastic block models SBMs. Specifically, we focus on edge differential privacy DP and propose private algorithms for community recovery. Our work explores the fundamental trade-offs between the privacy budget...

Enhancing Noisy Functional Encryption for Privacy-Preserving Machine Learning

Functional encryption FE has recently attracted interest in privacy-preserving machine learning PPML for its unique ability to compute specific functions on encrypted data. A related line of work focuses on noisy FE, which ensures differential privacy in the output while keeping the data encrypte...

UK Finfluencers: Exploring Content, Reach, and Responsibility

The rise of social media financial influencers finfluencers has significantly transformed the personal finance landscape, making financial advice and insights more accessible to a broader and younger audience. By leveraging digital platforms, these influencers have contributed to the...

Nuclei 3.4.3

Nuclei is a modern, high-performance vulnerability scanner that leverages simple YAML-based templates. It empowers you to design custom vulnerability detection scenarios that mimic real-world conditions, leading to zero false positives...

Apache ActiveMQ 6.1.6 Denial of Service

Apache ActiveMQ version 6.1.6 denial of service proof of concept exploit. This tool sends malicious OpenWire packets to exhaust the JVM heap memory of the target server, potentially crashing the ActiveMQ service on port 61616...

Engineering Risk-Aware, Security-By-Design Frameworks for Assurance of Large-Scale Autonomous AI Models

As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware, security-by-design approach for large-scale autonomous AI...

Privacy-Preserving Credit Card Approval Using Homomorphic SVM: toward Secure Inference in FinTech Applications

The growing use of machine learning in cloud environments raises critical concerns about data security and privacy, especially in finance. Fully Homomorphic Encryption FHE offers a solution by enabling computations on encrypted data, but its high computational cost limits practicality. In this...

Sparsification under Siege: Defending against Poisoning Attacks in Communication-Efficient Federated Learning

Federated Learning FL enables collaborative model training across distributed clients while preserving data privacy, yet it faces significant challenges in communication efficiency and vulnerability to poisoning attacks. While sparsification techniques mitigate communication overhead by...

System Prompt Poisoning: Persistent Attacks on Large Language Models beyond User Injection

Large language models LLMs have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through simple prompts. However, as LLMs become more integrated in...

Towards AI-Driven Human-Machine Co-Teaming for Adaptive and Agile Cyber Security Operation Centers

Security Operations Centers SOCs face growing challenges in managing cybersecurity threats due to an overwhelming volume of alerts, a shortage of skilled analysts, and poorly integrated tools. Human-AI collaboration offers a promising path to augment the capabilities of SOC analysts while reducin...

Security Steerability Is All You Need

The adoption of Generative AI GenAI in various applications inevitably comes with expanding the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate these security threats in GenAI by developing...

NCorr-FP: a Neighbourhood-Based Correlation-Preserving Fingerprinting Scheme for Intellectual Property Protection of Structured Data

Ensuring data ownership and traceability of unauthorised redistribution are central to safeguarding intellectual property in shared data environments. Data fingerprinting addresses these challenges by embedding recipient-specific marks into the data, typically via content modifications. We propos...

Comparing Classical and Quantum Conditional Disclosure of Secrets

The conditional disclosure of secrets CDS setting is among the most basic primitives studied in information-theoretic cryptography. Motivated by a connection to non-local quantum computation and position-based cryptography, CDS with quantum resources has recently been considered. Here, we study t...

Offensive Security for AI Systems: Concepts, Practices, and Applications

As artificial intelligence AI systems become increasingly adopted across sectors, the need for robust, proactive security strategies is paramount. Traditional defensive measures often fall short against the unique and evolving threats facing AI-driven technologies, making offensive security an...

XNU VM_BEHAVIOR_ZERO_WIRED_PAGES Page Write

There is an issue where XNU VMBEHAVIORZEROWIREDPAGES behavior allows writing to read-only pages...

Intrusion Detection System Using Deep Learning for Network Security

As the number of cyberattacks and their particualr nature escalate, the need for effective intrusion detection systems IDS has become indispensable for ensuring the security of contemporary networks. Adaptive and more sophisticated threats are often beyond the reach of traditional approaches to...

Learning from the Good Ones: Risk Profiling-Based Defenses against Evasion Attacks on DNNs

Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks DNN to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to trick the DNN into making wrong decisions at inference time...

Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense Via Model Pruning

Recent studies have shown that sponge attacks can significantly increase the energy consumption and inference latency of deep neural networks DNNs. However, prior work has focused primarily on computer vision and natural language processing tasks, overlooking the growing use of lightweight AI...

An Empirical Study of Fuzz Harness Degradation

The purpose of continuous fuzzing platforms is to enable fuzzing for software projects via \emphfuzz harnesses -- but as the projects continue to evolve, are these harnesses updated in lockstep, or do they run out of date? If these harnesses remain unmaintained, will they \emphdegrade over time i...

Invariant-Based Cryptography

We propose a new symmetric cryptographic scheme based on functional invariants defined over discrete oscillatory functions with hidden parameters. The scheme encodes a secret integer through a four-point algebraic identity preserved under controlled parameterization. Security arises not from...