Where the Devil Hides: Deepfake Detectors Can No Longer Be Trusted

With the advancement of AI generative techniques, Deepfake faces have become incredibly realistic and nearly indistinguishable to the human eye. To counter this, Deepfake detectors have been developed as reliable tools for assessing face authenticity. These detectors are typically developed on De...

On the Account Security Risks Posed by Password Strength Meters

Password strength meters PSMs have been widely used by websites to gauge password strength, encouraging users to create stronger passwords. Popular data-driven PSMs, e.g., based on Markov, Probabilistic Context-free Grammar PCFG and neural networks, alarm strength based on a model learned from re...

Measuring the Accuracy and Effectiveness of PII Removal Services

This paper presents the first large-scale empirical study of commercial personally identifiable information PII removal systems -- commercial services that claim to improve privacy by automating the removal of PII from data broker's databases. Popular examples of such services include DeleteMe,...

Quantum Support Vector Regression for Robust Anomaly Detection

Anomaly Detection AD is critical in data analysis, particularly within the domain of IT security. In recent years, Machine Learning ML algorithms have emerged as a powerful tool for AD in large-scale data. In this study, we explore the potential of quantum ML approaches, specifically quantum kern...

Cryptography without Long-Term Quantum Memory and Global Entanglement: Classical Setups for One-Time Programs, Copy Protection, and Stateful Obfuscation

We show how oracles which only allow for classical query access can be used to construct a variety of quantum cryptographic primitives which do not require long-term quantum memory or global entanglement. Specifically, if a quantum party can execute a semi-quantum token scheme Shmueli 2022 with...

The Sponge Is Quantum Indifferentiable

The sponge is a cryptographic construction that turns a public permutation into a hash function. When instantiated with the Keccak permutation, the sponge forms the NIST SHA-3 standard. SHA-3 is a core component of most post-quantum public-key cryptography schemes slated for worldwide adoption...

Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models

Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. Existing methods primarily focus on ensuring that watermark embedding doe...

iOS SwiftZero CVE-2025-24203 Proof of Concept

SwiftZero is a proof of concept exploit for iOS versions 16.0 through 18.3.2 that performs a protected file overwrite...

Nmap Port Scanner 7.97

Nmap is a utility for port scanning large networks, although it works fine for single hosts. Sometimes you need speed, other times you may need stealth. In some cases, bypassing firewalls may be required. Not to mention the fact that you may want to scan different protocols UDP, TCP, ICMP, etc...

Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores

The advent of convenient and efficient fully unmanned stores equipped with artificial intelligence-based automated checkout systems marks a new era in retail. However, these systems have inherent artificial intelligence security vulnerabilities, which are exploited via adversarial patch attacks,...

Red Teaming the Mind of the Machine: a Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Large Language Models LLMs are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation o...

Optimized Couplings for Watermarking Large Language Models

Large-language models LLMs are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of watermarks that imprint a signal'' in LLM-generated text with minimal perturbation of an LLM's output. This paper provides a...

Key Exchange Protocol Based on Circulant Matrix Action over Congruence-Simple Semiring

We present a new key exchange protocol based on circulant matrices acting on matrices over a congruence-simple semiring. We describe how to compute matrices with the necessary properties for the implementation of the protocol. Additionally, we provide an analysis of its computational cost and its...

Lightweight Hybrid Block-Stream Cryptographic Algorithm for the Internet of Things

In this thesis, a novel lightweight hybrid encryption algorithm named SEPAR is proposed, featuring a 16-bit block length and a 128-bit initialization vector. The algorithm is designed specifically for application in Internet of Things IoT technology devices. The design concept of this algorithm i...

Improved Algorithms for Differentially Private Language Model Alignment

Language model alignment is crucial for ensuring that large language models LLMs align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential privacy DP with alignment techniques, their performance...

Comparative Analysis of Blockchain Systems

Blockchain is a type of decentralized distributed database. Unlike traditional relational database management systems, it does not require management or maintenance by a third party. All data management and update processes are open and transparent, solving the trust issues of centralized databas...

Privacy-Preserving Analytics for Smart Meter (AMI) Data: a Hybrid Approach to Comply with CPUC Privacy Regulations

Advanced Metering Infrastructure AMI data from smart electric and gas meters enables valuable insights for utilities and consumers, but also raises significant privacy concerns. In California, regulatory decisions CPUC D.11-07-056 and D.11-08-045 mandate strict privacy protections for customer...

Kudzu: Fast and Simple High-Throughput BFT

We present Kudzu, a high-throughput atomic broadcast protocol with an integrated fast path. Our contribution is based on the combination of two lines of work. Firstly, our protocol achieves finality in just two rounds of communication if all but $p$ out of $n = 3f + 2p + 1$ participating replicas...

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...

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...

Federated Large Language Models: Feasibility, Robustness, Security and Future Directions

The integration of Large Language Models LLMs and Federated Learning FL presents a promising solution for joint training on distributed data while preserving privacy and addressing data silo issues. However, this emerging field, known as Federated Large Language Models FLLM, faces significant...

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...

Post-Quantum Secure Decentralized Random Number Generation Protocol with Two Rounds of Communication in the Standard Model

Randomness plays a vital role in numerous applications, including simulation, cryptography, distributed systems, and gaming. Consequently, extensive research has been conducted to generate randomness. One such method is to design a decentralized random number generator DRNG, a protocol that enabl...

Securing WiFi Fingerprint-Based Indoor Localization Systems from Malicious Access Points

WiFi fingerprint-based indoor localization schemes deliver highly accurate location data by matching the received signal strength indicator RSSI with an offline database using machine learning ML or deep learning DL models. However, over time, RSSI values degrade due to the malicious behavior of...

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...

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...

Mirror Mirror on the Wall, Have I Forgotten It All? A New Framework for Evaluating Machine Unlearning

Machine unlearning methods take a model trained on a dataset and a forget set, then attempt to produce a model as if it had only been trained on the examples not in the forget set. We empirically show that an adversary is able to distinguish between a mirror model a control model produced by...

A Large-Scale Empirical Analysis of Custom GPTs' Vulnerabilities in the OpenAI Ecosystem

Millions of users leverage generative pretrained transformer GPT-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms-such as OpenAI-now enable developers to create and publish tailored model...

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...

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...

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...

Assessing the Latency of Network Layer Security in 5G Networks

In contrast to its predecessors, 5G supports a wide range of commercial, industrial, and critical infrastructure scenarios. One key feature of 5G, ultra-reliable low latency communication, is particularly appealing to such scenarios for its real-time capabilities. However, 5G's enhanced security,...

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 ...

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 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...

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,...

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...

Zeek 7.0.7

Zeek is a powerful network analysis framework that is much different from the typical IDS you may know. While focusing on network security monitoring, Zeek provides a comprehensive platform for more general network traffic analysis as well. Well grounded in more than 15 years of research, Zeek ha...

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...

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...

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...

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...

Fair Play for Individuals, Foul Play for Groups? Auditing Anonymization'S Impact on ML Fairness

Machine learning ML algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers. This raises critical privacy concerns. Anonymization techniques have emerged as a practical solution to address these...

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...

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...

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...

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...

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...