Apple'S Synthetic Defocus Noise Pattern: Characterization and Forensic Applications

iPhone portrait-mode images contain a distinctive pattern in out-of-focus regions simulating the bokeh effect, which we term Apple's Synthetic Defocus Noise Pattern SDNP. If overlooked, this pattern can interfere with blind forensic analyses, especially PRNU-based camera source verification, as...

LLM-Text Watermarking Based on Lagrange Interpolation

The rapid advancement of LLMs Large Language Models has established them as a foundational technology for many AI and ML-powered human computer interactions. A critical challenge in this context is the attribution of LLM-generated text -- either to the specific language model that produced it or ...

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...

F5 BIG-IP 16.1.4.1 Remote Command Execution

F5 BIG-IP version 16.1.4.1 suffers from a command injection vulnerability via an authenticated user with administrator privileges...

WordPress Frontend Login and Registration Blocks 1.0.7 Privilege Escalation

WordPress Frontend Login and Registration Blocks plugin versions 1.0.7 and below are vulnerable to privilege escalation via account takeover. An unauthenticated attacker can change the administrator's email, trigger the Forgot Password process, and reset the admin password, gaining full control...

Invariant-Based Cryptography: toward a General Framework

We develop a generalized framework for invariant-based cryptography by extending the use of structural identities as core cryptographic mechanisms. Starting from a previously introduced scheme where a secret is encoded via a four-point algebraic invariant over masked functional values, we broaden...

Browser Security Posture Analysis: a Client-Side Security Assessment Framework

Modern web browsers have effectively become the new operating system for business applications, yet their security posture is often under-scrutinized. This paper presents a novel, comprehensive Browser Security Posture Analysis Framework1, a browser-based client-side security assessment toolkit...

Evaluating Explanation Quality in X-IDS Using Feature Alignment Metrics

Explainable artificial intelligence XAI methods have become increasingly important in the context of explainable intrusion detection systems X-IDSs for improving the interpretability and trustworthiness of X-IDSs. However, existing evaluation approaches for XAI focus on model-specific properties...

Self-Supervised Transformer-Based Contrastive Learning for Intrusion Detection Systems

As the digital landscape becomes more interconnected, the frequency and severity of zero-day attacks, have significantly increased, leading to an urgent need for innovative Intrusion Detection Systems IDS. Machine Learning-based IDS that learn from the network traffic characteristics and can...

LM-Scout: Analyzing the Security of Language Model Integration in Android Apps

Developers are increasingly integrating Language Models LMs into their mobile apps to provide features such as chat-based assistants. To prevent LM misuse, they impose various restrictions, including limits on the number of queries, input length, and allowed topics. However, if the LM integration...

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...

LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-Induced Risks and Vulnerabilities

The growing adoption of Large Language Models LLMs has influenced the development of their lighter counterparts-Small Language Models SLMs-to enable on-device deployment across smartphones and edge devices. These SLMs offer enhanced privacy, reduced latency, server-free functionality, and improve...

Private LoRA Fine-Tuning of Open-Source LLMs with Homomorphic Encryption

Preserving data confidentiality during the fine-tuning of open-source Large Language Models LLMs is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation LoRA technique for private fine-tuning. Homomorphic Encryption HE protects the...

WordPress PDF 2 Post 2.4.0 Shell Upload

WordPress PDF 2 Post plugin versions 2.4.0 and below suffers from a remote shell upload vulnerability via a zip file...

Valida ISA Spec, Version 1.0: a Zk-Optimized Instruction Set Architecture

The Valida instruction set architecture is designed for implementation in zkVMs to optimize for fast, efficient execution proving. This specification intends to guide implementors of zkVMs and compiler toolchains for Valida. It provides an unambiguous definition of the semantics of Valida program...

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...

GDNTT: an Area-Efficient Parallel NTT Accelerator Using Glitch-Driven Near-Memory Computing and Reconfigurable 10T SRAM

With the rapid advancement of quantum computing technology, post-quantum cryptography PQC has emerged as a pivotal direction for next-generation encryption standards. Among these, lattice-based cryptographic schemes rely heavily on the fast Number Theoretic Transform NTT over polynomial rings,...

Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity

With the growing use of large language models LLMs hosted on cloud platforms to offer inference services, privacy concerns about the potential leakage of sensitive information are escalating. Secure multi-party computation MPC is a promising solution to protect the privacy in LLM inference...

RedTeamLLM: an Agentic AI Framework for Offensive Security

From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leverag...

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,...

One Trigger Token Is Enough: a Defense Strategy for Balancing Safety and Usability in Large Language Models

Large Language Models LLMs have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the models into generating harmful responses despite safety...

TokenProber: Jailbreaking Text-To-Image Models Via Fine-Grained Word Impact Analysis

Text-to-image T2I models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work NSFW content, such as pornography, violence, political content, and discrimination. To mitigate the risk of generating NSFW...

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...

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...

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...

Standing Firm in 5G: a Single-Round, Dropout-Resilient Secure Aggregation for Federated Learning

Federated learning FL is well-suited to 5G networks, where many mobile devices generate sensitive edge data. Secure aggregation protocols enhance privacy in FL by ensuring that individual user updates reveal no information about the underlying client data. However, the dynamic and large-scale...

Securing Genomic Data against Inference Attacks in Federated Learning Environments

Federated Learning FL offers a promising framework for collaboratively training machine learning models across decentralized genomic datasets without direct data sharing. While this approach preserves data locality, it remains susceptible to sophisticated inference attacks that can compromise...

DP-TRAE: a Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

In the field of digital security, Reversible Adversarial Examples RAE combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks DNNs. However, existing RAE techniques primarily focus...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...