InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...

Pushing the Limits of Safety: a Technical Report on the ATLAS Challenge 2025

Multimodal Large Language Models MLLMs have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and improve their safety, we organized the Adversarial Testing...

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

Large vision-language models LVLMs have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used t...

Information-Theoretic Estimation of the Risk of Privacy Leaks

Recent work\citeLiu2016 has shown that dependencies between items in a dataset can lead to privacy leaks. We extend this concept to privacy-preserving transformations, considering a broader set of dependencies captured by correlation metrics. Specifically, we measure the correlation between the...

Semantic Preprocessing for LLM-Based Malware Analysis

In a context of malware analysis, numerous approaches rely on Artificial Intelligence to handle a large volume of data. However, these techniques focus on data view images, sequences and not on an expert's view. Noticing this issue, we propose a preprocessing that focuses on expert knowledge to...

A Lightweight IDS for Early APT Detection Using a Novel Feature Selection Method

An Advanced Persistent Threat APT is a multistage, highly sophisticated, and covert form of cyber threat that gains unauthorized access to networks to either steal valuable data or disrupt the targeted network. These threats often remain undetected for extended periods, emphasizing the critical...

LLM Embedding-Based Attribution (LEA): Quantifying Source Contributions to Generative Model'S Response for Vulnerability Analysis

Security vulnerabilities are rapidly increasing in frequency and complexity, creating a shifting threat landscape that challenges cybersecurity defenses. Large Language Models LLMs have been widely adopted for cybersecurity threat analysis. When querying LLMs, dealing with new, unseen...

A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis

Foundation models have gained growing interest in the IoT domain due to their reduced reliance on labeled data and strong generalizability across tasks, which address key limitations of traditional machine learning approaches. However, most existing foundation model based methods are developed fo...

Lessons for Cybersecurity from the American Public Health System

The United States needs national institutions and frameworks to systematically collect cybersecurity data, measure outcomes, and coordinate responses across government and private sectors, similar to how public health systems track and address disease outbreaks...

A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions

Modern large language models LLMs are often deployed as agents, calling external tools adaptively to solve tasks. Rather than directly calling tools, it can be more effective for LLMs to write code to perform the tool calls, enabling them to automatically generate complex control flow such as...

OSI Stack Redesign for Quantum Networks: Requirements, Technologies, Challenges, and Future Directions

Quantum communication is poised to become a foundational element of next-generation networking, offering transformative capabilities in security, entanglement-based connectivity, and computational offloading. However, the classical OSI model-designed for deterministic and error-tolerant...

Risks & Benefits of LLMs & GenAI for Platform Integrity, Healthcare Diagnostics, Cybersecurity, Privacy & AI Safety: a Comprehensive Survey, Roadmap & Implementation Blueprint

Large Language Models LLMs and generative AI GenAI systems such as ChatGPT, Claude, Gemini, LLaMA, and Copilot, developed by OpenAI, Anthropic, Google, Meta, and Microsoft are reshaping digital platforms and app ecosystems while introducing key challenges in cybersecurity, privacy, and platform...

Differential Privacy in Machine Learning: from Symbolic AI to LLMs

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorith...

Prohibited Items Segmentation Via Occlusion-Aware Bilayer Modeling

Instance segmentation of prohibited items in security X-ray images is a critical yet challenging task. This is mainly caused by the significant appearance gap between prohibited items in X-ray images and natural objects, as well as the severe overlapping among objects in X-ray images. To address...

The Domination and Secure Domination Numbers of Direct Product of Cliques with Paths and Cycles

In this paper, we obtain the exact values of several domination parameters for the direct product of a complete graph with a path or a cycle. Specifically, we determine the domination number, independent domination number, $1,2$-domination number, secure domination number, and 2-domination number...

Risks and Benefits of LLMs and GenAI for Platform Integrity, Healthcare Diagnostics, Cybersecurity, Privacy and AI Safety: a Comprehensive Survey, Roadmap and Implementation Blueprint

Large Language Models LLMs and generative AI GenAI systems such as ChatGPT, Claude, Gemini, LLaMA, and Copilot, developed by OpenAI, Anthropic, Google, Meta, and Microsoft are reshaping digital platforms and app ecosystems while introducing key challenges in cybersecurity, privacy, and platform...

PermRust: a Token-Based Permission System for Rust

Permission systems which restrict access to system resources are a well-established technology in operating systems, especially for smartphones. However, as such systems are implemented in the operating system they can at most manage access on the process-level. Since moderns software often reuse...

SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments

The increasing complexity of software has led to the steady growth of vulnerabilities. Vulnerability repair investigates how to fix software vulnerabilities. Manual vulnerability repair is labor-intensive and time-consuming because it relies on human experts, highlighting the importance of...

Leveraging GPT-4 for Vulnerability-Witnessing Unit Test Generation

In the life-cycle of software development, testing plays a crucial role in quality assurance. Proper testing not only increases code coverage and prevents regressions but it can also ensure that any potential vulnerabilities in the software are identified and effectively fixed. However, creating...

On Differential and Boomerang Properties of a Class of Binomials over Finite Fields of Odd Characteristic

In this paper, we investigate the differential and boomerang properties of a class of binomial $Fr,ux = x^r1 + uχx$ over the finite field $\mathbbFp^n$, where $r = \fracp^n+14$, $p^n \equiv 3 \pmod4$, and $χx = x^\fracp^n -12$ is the quadratic character in $\mathbbFp^n$. We show that $Fr,\pm1$ is...

FAA Framework: a Large Language Model-Based Approach for Credit Card Fraud Investigations

The continuous growth of the e-commerce industry attracts fraudsters who exploit stolen credit card details. Companies often investigate suspicious transactions in order to retain customer trust and address gaps in their fraud detection systems. However, analysts are overwhelmed with an enormous...

SecONNds: Secure Outsourced Neural Network Inference on ImageNet

The widespread adoption of outsourced neural network inference presents significant privacy challenges, as sensitive user data is processed on untrusted remote servers. Secure inference offers a privacy-preserving solution, but existing frameworks suffer from high computational overhead and...

Multi-Domain Anomaly Detection in a 5G Network

With the advent of 5G, mobile networks are becoming more dynamic and will therefore present a wider attack surface. To secure these new systems, we propose a multi-domain anomaly detection method that is distinguished by the study of traffic correlation on three dimensions: temporal by analyzing...

KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis

Binary code similarity analysis BCSA is a crucial research area in many fields such as cybersecurity. Specifically, function-level diffing tools are the most widely used in BCSA: they perform function matching one by one for evaluating the similarity between binary programs. However, such methods...

The Amazon Nova Family of Models: Technical Report and Model Card

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highly-capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks. Amazon...

Open Source, Open Threats? Investigating Security Challenges in Open-Source Software

Open-source software OSS has become increasingly more popular across different domains. However, this rapid development and widespread adoption come with a security cost. The growing complexity and openness of OSS ecosystems have led to increased exposure to vulnerabilities and attack surfaces...

Universal Jailbreak Suffixes Are Strong Attention Hijackers

We study suffix-based jailbreaks$\unicodex2013$a powerful family of attacks against large language models LLMs that optimize adversarial suffixes to circumvent safety alignment. Focusing on the widely used foundational GCG attack Zou et al., 2023, we observe that suffixes vary in efficacy: some...

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity

Large Language Models LLMs have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or...

Cost-Effective Optimization and Implementation of the CRT-Paillier Decryption Algorithm for Enhanced Performance

To address the privacy protection problem in cloud computing, privacy enhancement techniques such as the Paillier additive homomorphism algorithm are receiving widespread attention. Paillier algorithm allows addition and scalar multiplication operations in dencrypted state, which can effectively...

Organizational Adaptation to Generative AI in Cybersecurity: a Systematic Review

Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influenced by existing security maturity, regulatory requirements, and investments in human capital and infrastructure. This qualitative research employs...

MEraser: an Effective Fingerprint Erasure Approach for Large Language Models

Large Language Models LLMs have become increasingly prevalent across various sectors, raising critical concerns about model ownership and intellectual property protection. Although backdoor-based fingerprinting has emerged as a promising solution for model authentication, effective attacks for...

SoK: Current State of Ethereum'S Enshrined Proposer Builder Separation

Initially introduced to Ethereum via Flashbots' MEV-boost, Proposer-Builder Separation allows proposers to auction off blockspace to a market of transaction orderers, known as builders. PBS is currently available to validators through the aforementioned MEV-boost, but its unregulated and...

Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning

Differential privacy DP is obtained by randomizing a data analysis algorithm, which necessarily introduces a tradeoff between its utility and privacy. Many DP mechanisms are built upon one of two underlying tools: Laplace and Gaussian additive noise mechanisms. We expand the search space of...

On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification

What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where statistical effects due to limited data availability play a...

Restoring Gaussian Blurred Face Images for Deanonymization Attacks

Gaussian blur is widely used to blur human faces in sensitive photos before the photos are posted on the Internet. However, it is unclear to what extent the blurred faces can be restored and used to re-identify the person, especially under a high-blurring setting. In this paper, we explore this...

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates

Whitepaper called Differentially Private Bilevel Optimization: Efficient Algorithms With Near-Optimal Rates...

TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs

Chip manufacturing is a complex process, and to achieve a faster time to market, an increasing number of untrusted third-party tools and designs from around the world are being utilized. The use of these untrusted third party intellectual properties IPs and tools increases the risk of adversaries...

Technical Evaluation of a Disruptive Approach in Homomorphic AI

We present a technical evaluation of a new, disruptive cryptographic approach to data security, known as HbHAI Hash-based Homomorphic Artificial Intelligence. HbHAI is based on a novel class of key-dependent hash functions that naturally preserve most similarity properties, most AI algorithms rel...

Dynamic Temporal Positional Encodings for Early Intrusion Detection in IoT

The rapid expansion of the Internet of Things IoT has introduced significant security challenges, necessitating efficient and adaptive Intrusion Detection Systems IDS. Traditional IDS models often overlook the temporal characteristics of network traffic, limiting their effectiveness in early thre...

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs

Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigate the intriguing properties of adversarial examples in the frequency domain for the image classification task, with t...

Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information

LLM-based Conversational AIs CAIs, also known as GenAI chatbots, like ChatGPT, are increasingly used across various domains, but they pose privacy risks, as users may disclose personal information during their conversations with CAIs. Recent research has demonstrated that LLM-based CAIs could be...

QGuard:Question-Based Zero-Shot Guard for Multi-Modal LLM Safety

The recent advancements in Large Language ModelsLLMs have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the potential for malicious users to exploit harmful and jailbreak prompts for...

Investigating Vulnerabilities and Defenses against Audio-Visual Attacks: a Comprehensive Survey Emphasizing Multimodal Models

Multimodal large language models MLLMs, which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computation...

LLM-Based Dynamic Differential Testing for Database Connectors with Reinforcement Learning-Guided Prompt Selection

Database connectors are critical components enabling applications to interact with underlying database management systems DBMS, yet their security vulnerabilities often remain overlooked. Unlike traditional software defects, connector vulnerabilities exhibit subtle behavioral patterns and are...

Privacy-Preserving and Reward-Based Mechanisms of Proof of Engagement

Proof-of-Attendance PoA mechanisms are typically employed to demonstrate a specific user's participation in an event, whether virtual or in-person. The goal of this study is to extend such mechanisms to broader contexts where the user wishes to digitally demonstrate her involvement in a specific...

InfoFlood: Jailbreaking Large Language Models with Information Overload

Large Language Models LLMs have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing...

Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT

Address Resolution Protocol ARP spoofing attacks severely threaten Internet of Things IoT networks by allowing attackers to intercept, modify, or block communications. Traditional detection methods are insufficient due to high false positives and poor adaptability. This research proposes a...

LURK-T: Limited Use of Remote Keys with Added Trust in TLS 1.3

In many web applications, such as Content Delivery Networks CDNs, TLS credentials are shared, e.g., between the website's TLS origin server and the CDN's edge servers, which can be distributed around the globe. To enhance the security and trust for TLS 1.3 in such scenarios, we propose LURK-T, a...

Leakage-Resilient Extractors against Number-On-Forehead Protocols

Given a sequence of $N$ independent sources $\mathbfX1,\mathbfX2,\dots,\mathbfXN\sim\0,1^n$, how many of them must be good i.e., contain some min-entropy in order to extract a uniformly random string? This question was first raised by Chattopadhyay, Goodman, Goyal and Li STOC '20, motivated by...

PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-Using-DRAM in Real DRAM Chips

Processing-using-DRAM PuD is a promising paradigm for alleviating the data movement bottleneck using DRAM's massive internal parallelism and bandwidth to execute very wide operations. Performing a PuD operation involves activating multiple DRAM rows in quick succession or simultaneously, i.e.,...