What Really Is a Member? Discrediting Membership Inference Via Poisoning

Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often fail under the strict definition of membership based on exact matching, and have suggested relaxing this definition t...

PrivTru: a Privacy-By-Design Data Trustee Minimizing Information Leakage

Data trustees serve as intermediaries that facilitate secure data sharing between independent parties. This paper offers a technical perspective on Data trustees, guided by privacy-by-design principles. We introduce PrivTru, an instantiation of a data trustee that provably achieves optimal privac...

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models

The protection of cyber Intellectual Property IP such as web content is an increasingly critical concern. The rise of large language models LLMs with online retrieval capabilities enables convenient access to information but often undermines the rights of original content creators. As users...

SATversary: Adversarial Attacks on Satellite Fingerprinting

As satellite systems become increasingly vulnerable to physical layer attacks via SDRs, novel countermeasures are being developed to protect critical systems, particularly those lacking cryptographic protection, or those which cannot be upgraded to support modern cryptography. Among these is...

Stealix: Model Stealing Via Prompt Evolution

Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information. Recent methods that use pre-trained diffusion models for data...

Conformal-DP: Data Density Aware Privacy on Riemannian Manifolds Via Conformal Transformation

Whitepaper called Conformal-DP: Data Density Aware Privacy On Riemannian Manifolds Via Conformal Transformation...

Synthetic Tabular Data: Methods, Attacks and Defenses

Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much progress in synthetic data generation over the last decade, leveraging corresponding advances in machine learning an...

Membership Inference Attacks for Unseen Classes

Shadow model attacks are the state-of-the-art approach for membership inference attacks on machine learning models. However, these attacks typically assume an adversary has access to a background nonmember data distribution that matches the distribution the target model was trained on. We initiat...

Detecting and Mitigating SQL Injection Vulnerabilities in Web Applications

SQL injection SQLi remains a critical vulnerability in web applications, enabling attackers to manipulate databases through malicious inputs. Despite advancements in mitigation techniques, the evolving complexity of web applications and attack strategies continues to pose significant risks. This...

There'S Waldo: PCB Tamper Forensic Analysis Using Explainable AI on Impedance Signatures

The security of printed circuit boards PCBs has become increasingly vital as supply chain vulnerabilities, including tampering, present significant risks to electronic systems. While detecting tampering on a PCB is the first step for verification, forensics is also needed to identify the modified...

FIST: a Structured Threat Modeling Framework for Fraud Incidents

Fraudulent activities are rapidly evolving, employing increasingly diverse and sophisticated methods that pose serious threats to individuals, organizations, and society. This paper proposes the FIST Framework Fraud Incident Structured Threat Framework, an innovative structured threat modeling...

GNUnet P2P Framework 0.24.2

GNUnet is a peer-to-peer framework with focus on providing security. All peer-to-peer messages in the network are confidential and authenticated. The framework provides a transport abstraction layer and can currently encapsulate the network traffic in UDP IPv4 and IPv6, TCP IPv4 and IPv6, HTTP, o...

To Protect the LLM Agent against the Prompt Injection Attack with Polymorphic Prompt

LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inputs manipulate the model's behavior. Traditional defenses like input sanitization, guard models, and guardrails are...

Adapting under Fire: Multi-Agent Reinforcement Learning for Adversarial Drift in Network Security

Evolving attacks are a critical challenge for the long-term success of Network Intrusion Detection Systems NIDS. The rise of these changing patterns has exposed the limitations of traditional network security methods. While signature-based methods are used to detect different types of attacks, th...

Faraday 5.14.1

Faraday is a tool that introduces a new concept called IPE, or Integrated Penetration-Test Environment. It is a multiuser penetration test IDE designed for distribution, indexation and analysis of the generated data during the process of a security audit. The main purpose of Faraday is to re-use...

The Complexity of the SupportMinors Modeling for the MinRank Problem

In this note, we provide proven estimates for the complexity of the SupportMinors Modeling, mostly confirming the heuristic complexity estimates contained in the original article...

When Better Features Mean Greater Risks: the Performance-Privacy Trade-Off in Contrastive Learning

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their widespread use has raised significant concerns about the risk o...

The Scales of Justitia: a Comprehensive Survey on Safety Evaluation of LLMs

With the rapid advancement of artificial intelligence technology, Large Language Models LLMs have demonstrated remarkable potential in the field of Natural Language Processing NLP, including areas such as content generation, human-computer interaction, machine translation, and code generation,...

Combating Reentrancy Bugs on Sharded Blockchains

Reentrancy is a well-known source of smart contract bugs on Ethereum, leading e.g. to double-spending vulnerabilities in DeFi applications. But less is known about this problem in other blockchains, which can have significantly different execution models. Sharded blockchains in particular general...

Breaking the Gaussian Barrier: Residual-PAC Privacy for Automatic Privatization

The Probably Approximately Correct PAC Privacy framework 1 provides a powerful instance-based methodology for certifying privacy in complex data-driven systems. However, existing PAC Privacy algorithms rely on a Gaussian mutual information upper bound. We show that this is in general too...

Cyber Security of Sensor Systems for State Sequence Estimation: an AI Approach

Sensor systems are extremely popular today and vulnerable to sensor data attacks. Due to possible devastating consequences, counteracting sensor data attacks is an extremely important topic, which has not seen sufficient study. This paper develops the first methods that accurately...

GeoClip: Geometry-Aware Clipping for Differentially Private SGD

Differentially private stochastic gradient descent DP-SGD is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping threshold, which significantly affects the trade-off between privac...

Benchmarking Misuse Mitigation against Covert Adversaries

Existing language model safety evaluations focus on overt attacks and low-stakes tasks. Realistic attackers can subvert current safeguards by requesting help on small, benign-seeming tasks across many independent queries. Because individual queries do not appear harmful, the attack is hard to...

Depermissioning Web3: a Permissionless Accountable RPC Protocol for Blockchain Networks

In blockchain networks, so-called "full nodes" serve data to and relay transactions from clients through an RPC interface. This serving layer enables integration of "Web3" data, stored on blockchains, with "Web2" mobile or web applications that cannot directly participate as peers in a blockchain...

Securing Traffic Sign Recognition Systems in Autonomous Vehicles

Deep Neural Networks DNNs are widely used for traffic sign recognition because they can automatically extract high-level features from images. These DNNs are trained on large-scale datasets obtained from unknown sources. Therefore, it is important to ensure that the models remain secure and are n...

NIH BRICS 14.0.0-67 Predictable Tokens

NIH BRICS aka Biomedical Research Informatics Computing System through 14.0.0-67 generates predictable tokens that depend on username, time, and the fixed 7Dl9dj- string and thus allows unauthenticated users with a Common Access Card CAC to escalate privileges and compromise any account, includin...

Rethinking Machine Unlearning in Image Generation Models

With the surge and widespread application of image generation models, data privacy and content safety have become major concerns and attracted great attention from users, service providers, and policymakers. Machine unlearning MU is recognized as a cost-effective and promising means to address...

Inclusive, Differentially Private Federated Learning for Clinical Data

Federated Learning FL offers a promising approach for training clinical AI models without centralizing sensitive patient data. However, its real-world adoption is hindered by challenges related to privacy, resource constraints, and compliance. Existing Differential Privacy DP approaches often app...

On Automating Security Policies with Contemporary LLMs

The complexity of modern computing environments and the growing sophistication of cyber threats necessitate a more robust, adaptive, and automated approach to security enforcement. In this paper, we present a framework leveraging large language models LLMs for automating attack mitigation policy...

Authenticated Private Set Intersection: a Merkle Tree-Based Approach for Enhancing Data Integrity

Private Set Intersection PSI enables secure computation of set intersections while preserving participant privacy, standard PSI existing protocols remain vulnerable to data integrity attacks allowing malicious participants to extract additional intersection information or mislead other parties. I...

Breaking Anonymity at Scale: Re-Identifying the Trajectories of 100K Real Users in Japan

Mobility traces represent a critical class of personal data, often subjected to privacy-preserving transformations before public release. In this study, we analyze the anonymized Yjmob100k dataset, which captures the trajectories of 100,000 users in Japan, and demonstrate how existing anonymizati...

Network Hexagons under Attack: Secure Crowdsourcing of Geo-Referenced Data

A critical requirement for modern-day Intelligent Transportation Systems ITS is the ability to collect geo-referenced data from connected vehicles and mobile devices in a safe, secure and anonymous way. The Nexagon protocol, which builds on the IETF Locator/ID Separation Protocol LISP and the...

Why LLM Safety Guardrails Collapse after Fine-Tuning: a Similarity Analysis between Alignment and Fine-Tuning Datasets

Recent advancements in large language models LLMs have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies primarily focus on reactively addressing jailbreak incidents after safety guardrail...

Hybrid Stabilization Protocol for Cross-Chain Digital Assets Using Adaptor Signatures and AI-Driven Arbitrage

Stablecoins face an unresolved trilemma of balancing decentralization, stability, and regulatory compliance. We present a hybrid stabilization protocol that combines crypto-collateralized reserves, algorithmic futures contracts, and cross-chain liquidity pools to achieve robust price adherence...

EMBER2024 -- a Benchmark Dataset for Holistic Evaluation of Malware Classifiers

A lack of accessible data has historically restricted malware analysis research, and practitioners have relied heavily on datasets provided by industry sources to advance. Existing public datasets are limited by narrow scope - most include files targeting a single platform, have labels supporting...

SECNEURON: Reliable and Flexible Abuse Control in Local LLMs Via Hybrid Neuron Encryption

Large language models LLMs with diverse capabilities are increasingly being deployed in local environments, presenting significant security and controllability challenges. These locally deployed LLMs operate outside the direct control of developers, rendering them more susceptible to abuse...

SoK: Are Watermarks in LLMs Ready for Deployment?

Large Language Models LLMs have transformed natural language processing, demonstrating impressive capabilities across diverse tasks. However, deploying these models introduces critical risks related to intellectual property violations and potential misuse, particularly as adversaries can imitate...

TracLLM: a Generic Framework for Attributing Long Context LLMs

Long context large language models LLMs are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long context e.g., documents, PDF files, webpages, a long context LLM can generate an output grounded in the provided context,...

OpenCCA: an Open Framework to Enable Arm CCA Research

Confidential computing has gained traction across major architectures with Intel TDX, AMD SEV-SNP, and Arm CCA. Unlike TDX and SEV-SNP, a key challenge in researching Arm CCA is the absence of hardware support, forcing researchers to develop ad-hoc performance prototypes on non-CCA Arm boards. Th...

Private Key and Password Protection by Steganographic Image Encryption

We propose a technique to protect and preserve a private key or a passcode in an encrypted two-dimensional graphical image. The plaintext private key or the passcode is converted into an encrypted QR code and embedded into a real-life color image with a steganographic scheme. The private key or t...

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

The honesty of large language models LLMs is a critical alignment challenge, especially as advanced systems with chain-of-thought CoT reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be possibly explained as some kind of hallucination, those model...

Evaluating the Impact of Privacy-Preserving Federated Learning on CAN Intrusion Detection

The challenges derived from the data-intensive nature of machine learning in conjunction with technologies that enable novel paradigms such as V2X and the potential offered by 5G communication, allow and justify the deployment of Federated Learning FL solutions in the vehicular intrusion detectio...

tc Tor Chat Client 1.2

tc is a low-tech free solution to make yourself anonymously reachable for chat by anyone who only know your onion address and your public key. Messages are PGP encrypted end-to-end and forwarded by Tor's relays. Please note this tarball's hash will not match the main release hash on the tor site ...

StealthInk: a Multi-Bit and Stealthy Watermark for Large Language Models

Watermarking for large language models LLMs offers a promising approach to identifying AI-generated text. Existing approaches, however, either compromise the distribution of original generated text by LLMs or are limited to embedding zero-bit information that only allows for watermark detection b...

Incentivizing Collaborative Breach Detection

Decoy passwords, or "honeywords," alert a site to its breach if they are ever entered in a login attempt on that site. However, an attacker can identify a user-chosen password from among the decoys, without risk of alerting the site to its breach, by performing credential stuffing, i.e., entering...

MULTISS: Un Protocole De Stockage Confidentiel {À} Long Terme Sur Plusieurs R{É}Seaux QKD

This paper presents MULTISS, a new protocol for long-term storage distributed across multiple Quantum Key Distribution QKD networks. This protocol is an extension of LINCOS, a secure storage protocol that uses Shamir secret sharing for secret storage on a single QKD network. Our protocol uses...

Attack Effect Model Based Malicious Behavior Detection

Traditional security detection methods face three key challenges: inadequate data collection that misses critical security events, resource-intensive monitoring systems, and poor detection algorithms with high false positive rates. We present FEAD Focus-Enhanced Attack Detection, a framework that...

A Private Smart Wallet with Probabilistic Compliance

We propose a privacy-preserving smart wallet with a novel invitation-based private onboarding mechanism. The solution integrates two levels of compliance in concert with an authority party: a proof of innocence mechanism and an ancestral commitment tracking system using bloom filters for...

A Symmetric LWE-Based Multi-Recipient Cryptosystem

This article describes a post-quantum multirecipient symmetric cryptosystem whose security is based on the hardness of the LWE problem. In this scheme a single sender encrypts multiple messages for multiple recipients generating a single ciphertext which is broadcast to the recipients. Each...

Sentinel: SOTA Model to Protect against Prompt Injections

Large Language Models LLMs are increasingly powerful but remain vulnerable to prompt injection attacks, where malicious inputs cause the model to deviate from its intended instructions. This paper introduces Sentinel, a novel detection model, qualifire/prompt-injection-sentinel, based on the...