Certified Unlearning for Neural Networks

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to be forgotten." Unfortunately, existing methods rely on restrictive assumptio...

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test

As API access becomes a primary interface to large language models LLMs, users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API providers may discreetly serve quantized or fine-tuned variants,...

Lightweight Electronic Signatures and Reliable Access Control Included in Sensor Networks to Prevent Cyber Attacks from Modifying Patient Data

Digital terrorism is a major cause of securing patient/healthcare providers data and information. Sensitive topics that may have an impact on a patient's health or even national security include patient health records and information on healthcare providers. Health databases and data sets have be...

WGLE:Backdoor-Free and Multi-Bit Black-Box Watermarking for Graph Neural Networks

Graph Neural Networks GNNs are increasingly deployed in graph-related applications, making ownership verification critical to protect their intellectual property against model theft. Fingerprinting and black-box watermarking are two main methods. However, the former relies on determining model...

"Vcd2df" -- Leveraging Data Science Insights for Hardware Security Research

In this work, we hope to expand the universe of security practitioners of open-source hardware by creating a bridge from hardware design languages HDLs to data science languages like Python and R through novel libraries that convert VCD value change dump files into data frames, the expected input...

Network Threat Detection: Addressing Class Imbalanced Data with Deep Forest

With the rapid expansion of Internet of Things IoT networks, detecting malicious traffic in real-time has become a critical cybersecurity challenge. This research addresses the detection challenges by presenting a comprehensive empirical analysis of machine learning techniques for malware detecti...

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges

The widespread adoption of Large Language Models LLMs has heightened concerns about their security, particularly their vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs. While prior research has been conducted on general security capabilities of LLMs,...

Gh0stEdit: Exploiting Layer-Based Access Vulnerability within Docker Container Images

Whitepaper called Gh0stEdit: Exploiting Layer-Based Access Vulnerability Within Docker Container Images...

WordPress Spreadsheet Price Changer 2.4.37 Privilege Escalation

WordPress Spreadsheet Price Changer plugin versions 2.4.37 and below suffer from a privilege escalation vulnerability...

Stark-Coleman Invariants and Quantum Lower Bounds: an Integrated Framework for Real Quadratic Fields

Class groups of real quadratic fields represent fundamental structures in algebraic number theory with significant computational implications. While Stark's conjecture establishes theoretical connections between special units and class group structures, explicit constructions have remained elusiv...

Unraveling Ethereum'S Mempool: the Impact of Fee Fairness, Transaction Prioritization, and Consensus Efficiency

Ethereum's transaction pool mempool dynamics and fee market efficiency critically affect transaction inclusion, validator workload, and overall network performance. This research empirically analyzes gas price variations, mempool clearance rates, and block finalization times in Ethereum's...

Understanding the Error Sensitivity of Privacy-Aware Computing

Homomorphic Encryption HE enables secure computation on encrypted data without decryption, allowing a great opportunity for privacy-preserving computation. In particular, domains such as healthcare, finance, and government, where data privacy and security are of utmost importance, can benefit fro...

Exposing Hidden Backdoors in NFT Smart Contracts: a Static Security Analysis of Rug Pull Patterns

The explosive growth of Non-Fungible Tokens NFTs has revolutionized digital ownership by enabling the creation, exchange, and monetization of unique assets on blockchain networks. However, this surge in popularity has also given rise to a disturbing trend: the emergence of rug pulls - fraudulent...

Attacking Attention of Foundation Models Disrupts Downstream Tasks

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning. For this reason, models such as CLIP , DINO or Vision...

A Red Teaming Roadmap Towards System-Level Safety

Large Language Model LLM safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine learning and AI safety, safeguard red teaming has effectively identified critical vulnerabilities in state-of-the-art...

How Good LLM-Generated Password Policies Are?

Generative AI technologies, particularly Large Language Models LLMs, are rapidly being adopted across industry, academia, and government sectors, owing to their remarkable capabilities in natural language processing. However, despite their strengths, the inconsistency and unpredictability of LLM...

Doxing Via the Lens: Revealing Location-Related Privacy Leakage on Multi-Modal Large Reasoning Models

Recent advances in multi-modal large reasoning models MLRMs have shown significant ability to interpret complex visual content. While these models enable impressive reasoning capabilities, they also introduce novel and underexplored privacy risks. In this paper, we identify a novel category of...

Distortion Search, a Web Search Privacy Heuristic

Search engines have vast technical capabilities to retain Internet search logs for each user and thus present major privacy vulnerabilities to both individuals and organizations in revealing user intent. Additionally, many of the web search privacy enhancing tools available today require that the...

Towards Generalized Source Tracing for Codec-Based Deepfake Speech

Recent attempts at source tracing for codec-based deepfake speech CodecFake, generated by neural audio codec-based speech generation CoSG models, have exhibited suboptimal performance. However, how to train source tracing models using simulated CoSG data while maintaining strong performance on re...

Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms

We analyze two open source deep reinforcement learning agents submitted to the CAGE Challenge 2 cyber defense challenge, where each competitor submitted an agent to defend a simulated network against each of several provided rules-based attack agents. We demonstrate that one can gain...

Profiling Electric Vehicles Via Early Charging Voltage Patterns

Electric Vehicles EVs are rapidly gaining adoption as a sustainable alternative to fuel-powered vehicles, making secure charging infrastructure essential. Despite traditional authentication protocols, recent results showed that attackers may steal energy through tailored relay attacks. One...

Secure Distributed Learning for CAVs: Defending against Gradient Leakage with Leveled Homomorphic Encryption

Federated Learning FL enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning in domains like Connected and Autonomous Vehicles CAVs. However, recent studies have shown that exchanged model...

A Systematic Literature Review on Continuous Integration and Deployment (CI/CD) for Secure Cloud Computing

As cloud environments become widespread, cybersecurity has emerged as a top priority across areas such as networks, communication, data privacy, response times, and availability. Various sectors, including industries, healthcare, and government, have recently faced cyberattacks targeting their...

Private Evolution Converges

Private Evolution PE is a promising training-free method for differentially private DP synthetic data generation. While it achieves strong performance in some domains e.g., images and text, its behavior in others e.g., tabular data is less consistent. To date, the only theoretical analysis of the...

Minoritised Ethnic People'S Security and Privacy Concerns and Responses Towards Essential Online Services

Minoritised ethnic people are marginalised in society, and therefore at a higher risk of adverse online harms, including those arising from the loss of security and privacy of personal data. Despite this, there has been very little research focused on minoritised ethnic people's security and...

Correlated Noise Mechanisms for Differentially Private Learning

This monograph explores the design and analysis of correlated noise mechanisms for differential privacy DP, focusing on their application to private training of AI and machine learning models via the core primitive of estimation of weighted prefix sums. While typical DP mechanisms inject...

PoSyn: Secure Power Side-Channel Aware Synthesis

Power Side-Channel PSC attacks exploit power consumption patterns to extract sensitive information, posing risks to cryptographic operations crucial for secure systems. Traditional countermeasures, such as masking, face challenges including complex integration during synthesis, substantial area...

Are Trees Really Green? A Detection Approach of IoT Malware Attacks

Nowadays, the Internet of Things IoT is widely employed, and its usage is growing exponentially because it facilitates remote monitoring, predictive maintenance, and data-driven decision making, especially in the healthcare and industrial sectors. However, IoT devices remain vulnerable due to the...

Mind the Gap: Revealing Security Barriers through Situational Awareness of Small and Medium Business Key Decision-Makers

Key decision-makers in small and medium businesses SMBs often lack the awareness and knowledge to implement cybersecurity measures effectively. To gain a deeper understanding of how SMB executives navigate cybersecurity decision-making, we deployed a mixed-method approach, conducting...

LLM Unlearning Should Be Form-Independent

Large Language Model LLM unlearning aims to erase or suppress undesirable knowledge within the model, offering promise for controlling harmful or private information to prevent misuse. However, recent studies highlight its limited efficacy in real-world scenarios, hindering practical adoption. In...

MalGEN: a Generative Agent Framework for Modeling Malicious Software in Cybersecurity

The dual use nature of Large Language Models LLMs presents a growing challenge in cybersecurity. While LLM enhances automation and reasoning for defenders, they also introduce new risks, particularly their potential to be misused for generating evasive, AI crafted malware. Despite this emerging...

Securing Unbounded Differential Privacy against Timing Attacks

Recent works have started to theoretically investigate how we can protect differentially private programs against timing attacks, by making the joint distribution the output and the runtime differentially private JOT-DP. However, the existing approaches to JOT-DP have some limitations, particular...

Data-Driven Understanding of Security Issue Reporting in GitHub Repositories of Open Source Npm Packages

The npm Node Package Manager ecosystem is the most important package manager for JavaScript development with millions of users. Consequently, a plethora of earlier work investigated how vulnerability reporting, patch propagation, and in general detection as well as resolution of security issues i...

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models

Large Language Models LLMs memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information PII, which should not be stored and, consequently, not leaked. In this paper, we introduce Private Memorization Editing PME, an approach for preventing private...

CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack

Projector-based adversarial attack aims to project carefully designed light patterns i.e., adversarial projections onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of more robust classifiers. However, existing approaches...

GradEscape: a Gradient-Based Evader against AI-Generated Text Detectors

In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text AIGT detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for t...

IF-GUIDE: Influence Function-Guided Detoxification of LLMs

We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained and potentially toxic models to align them with human values. In contrast, we propose a...

SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense

Traditional deep neural networks suffer from several limitations, including catastrophic forgetting. When models are adapted to new datasets, they tend to quickly forget previously learned knowledge. Another significant issue is the lack of robustness to even small perturbations in the input data...

Explainable AI for Enhancing IDS against Advanced Persistent Kill Chain

Advanced Persistent Threats APTs represent a sophisticated and persistent cy-bersecurity challenge, characterized by stealthy, multi-phase, and targeted attacks aimed at compromising information systems over an extended period. Develop-ing an effective Intrusion Detection System IDS capable of...

SoK: Data Reconstruction Attacks against Machine Learning Models: Definition, Metrics, and Benchmark

Data reconstruction attacks, which aim to recover the training dataset of a target model with limited access, have gained increasing attention in recent years. However, there is currently no consensus on a formal definition of data reconstruction attacks or appropriate evaluation metrics for...

Evaluating Explainable AI for Deep Learning-Based Network Intrusion Detection System Alert Classification

A Network Intrusion Detection System NIDS monitors networks for cyber attacks and other unwanted activities. However, NIDS solutions often generate an overwhelming number of alerts daily, making it challenging for analysts to prioritize high-priority threats. While deep learning models promise to...

TokenBreak: Bypassing Text Classification Models through Token Manipulation

Natural Language Processing NLP models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling it to make inferences and understand context. Text...

Walrus: an Efficient Decentralized Storage Network

Decentralized storage systems face a fundamental trade-off between replication overhead, recovery efficiency, and security guarantees. Current approaches either rely on full replication, incurring substantial storage costs, or employ trivial erasure coding schemes that struggle with efficient...

Insecurity through Obscurity: Veiled Vulnerabilities in Closed-Source Contracts

Most blockchains cannot hide the binary code of programs i.e., smart contracts running on them. To conceal proprietary business logic and to potentially deter attacks, many smart contracts are closed-source and employ layers of obfuscation. However, we demonstrate that such obfuscation can obscur...

Pixel-Sensitive and Robust Steganography Based on Polar Codes

Steganography is an information hiding technique for covert communication. The core issue in steganography design is the rate-distortion coding problem. Polar codes, which have been proven to achieve the rate-distortion bound for any binary symmetric source, are utilized to design a steganographi...

D2R: Dual Regularization Loss with Collaborative Adversarial Generation for Model Robustness

The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to enhance model robustness. Two key limitations of existing methods are i insufficient guidance of the target model via...

SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

Large language models LLMs have seen widespread success in code generation tasks for different scenarios, both everyday and professional. However current LLMs, despite producing functional code, do not prioritize security and may generate code with exploitable vulnerabilities. In this work, we...

STAMP Your Content: Proving Dataset Membership Via Watermarked Rephrasings

Given how large parts of publicly available text are crawled to pretrain large language models LLMs, data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their concerns are also shared by benchmark curators whose...

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an effective approach for enhancing LLM safety by adding a refusal...

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Vision Language Models VLMs have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of...