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...

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...

Reversing the Paradigm: Building AI-First Systems with Human Guidance

The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs into everyday life, powering customer service chats, personalizing travel, aiding doctors in diagnosis, and supporti...

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...

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...

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...

IDOL: Improved Different Optimization Levels Testing for Solidity Compilers

As blockchain technology continues to evolve and mature, smart contracts have become a key driving force behind the digitization and automation of transactions. Smart contracts greatly simplify and refine the traditional business transaction processes, and thus have had a profound impact on vario...

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...

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...

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...

SmartHome-Bench: a Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models

Video anomaly detection VAD is essential for enhancing safety and security by identifying unusual events across different environments. Existing VAD benchmarks, however, are primarily designed for general-purpose scenarios, neglecting the specific characteristics of smart home applications. To...

Cut Tracing with E-Graphs for Boolean FHE Circuit Synthesis

Fully Homomorphic Encryption FHE is a promising privacy-preserving technology enabling secure computation over encrypted data. A major limitation of current FHE schemes is their high runtime overhead. As a result, automatic optimization of circuits describing FHE computation has garnered...

FAME: a Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes

The widespread emergence of face-swap Deepfake videos poses growing risks to digital security, privacy, and media integrity, necessitating effective forensic tools for identifying the source of such manipulations. Although most prior research has focused primarily on binary Deepfake detection, th...

Robot Context Protocol (RCP): a Runtime-Agnostic Interface for Agent-Aware Robot Control

The Robot Context Protocol RCP is a lightweight, middleware-agnostic communication protocol designed to simplify the complexity of robotic systems and enable seamless interaction between robots, users, and autonomous agents. RCP provides a unified and semantically meaningful interface that...

Leveraging Photonic Interconnects for Scalable and Efficient Fully Homomorphic Encryption

Fully Homomorphic Encryption FHE facilitates secure computations on encrypted data but imposes significant demands on memory bandwidth and computational power. While current FHE accelerators focus on optimizing computation, they often face bandwidth limitations that result in performance...

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...

UCD: Unlearning in LLMs Via Contrastive Decoding

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models LLMs while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive decoding, leveraging two auxiliary smaller models, one train...

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...

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...

Versatile and Fast Location-Based Private Information Retrieval with Fully Homomorphic Encryption over the Torus

Location-based services often require users to share sensitive locational data, raising privacy concerns due to potential misuse or exploitation by untrusted servers. In response, we present VeLoPIR, a versatile location-based private information retrieval PIR system designed to preserve user...

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...

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...

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...

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...

Towards Safety and Security Testing of Cyberphysical Power Systems by Shape Validation

The increasing complexity of cyberphysical power systems leads to larger attack surfaces to be exploited by malicious actors and a higher risk of faults through misconfiguration. We propose to meet those risks with a declarative approach to describe cyberphysical power systems and to automaticall...

Today'S Cat Is Tomorrow'S Dog: Accounting for Time-Based Changes in the Labels of ML Vulnerability Detection Approaches

Vulnerability datasets used for ML testing implicitly contain retrospective information. When tested on the field, one can only use the labels available at the time of training and testing e.g. seen and assumed negatives. As vulnerabilities are discovered across calendar time, labels change and...

Privacy-Preserving Federated Learning against Malicious Clients Based on Verifiable Functional Encryption

Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protect data privacy. However, it also brings new threats and challenges. The advancement of model inversion attacks has rendered the plaintext...

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...

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: a New Inference Attack Perspective

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent to retraining, it is impractical for large-scale models, leading to growing...

DinoCompanion: an Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction

Children's emotional development fundamentally relies on secure attachment relationships, yet current AI companions lack the theoretical foundation to provide developmentally appropriate emotional support. We introduce DinoCompanion, the first attachment-theory-grounded multimodal robot for...

Smart Buildings Energy Consumption Forecasting Using Adaptive Evolutionary Ensemble Learning Models

Smart buildings are gaining popularity because they can enhance energy efficiency, lower costs, improve security, and provide a more comfortable and convenient environment for building occupants. A considerable portion of the global energy supply is consumed in the building sector and plays a...

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...

KCLNet: Physics-Informed Power Flow Prediction Via Constraints Projections

In the modern context of power systems, rapid, scalable, and physically plausible power flow predictions are essential for ensuring the grid's safe and efficient operation. While traditional numerical methods have proven robust, they require extensive computation to maintain physical fidelity und...

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks Via Security-Aware Prompt Compression

Large language models LLMs have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by wrapping the original malicious instructions inside adversarial...

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...

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...

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...

An Attack Method for Medical Insurance Claim Fraud Detection Based on Generative Adversarial Network

Insurance fraud detection represents a pivotal advancement in modern insurance service, providing intelligent and digitalized monitoring to enhance management and prevent fraud. It is crucial for ensuring the security and efficiency of insurance systems. Although AI and machine learning algorithm...

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...

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...

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...

Mechanistic Interpretability in the Presence of Architectural Obfuscation

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving large-language-model LLM inference. While recent work has sho...

An Efficient Hardware Implementation of Elliptic Curve Point Multiplication over $GF(2^M)$ on FPGA

Elliptic Curve Cryptography ECC is widely accepted for ensuring secure data exchange between resource-limited IoT devices. The National Institute of Standards and Technology NIST recommended implementation, such as B-163, is particularly well-suited for Internet of Things IoT applications. Here,...

Exploring the Secondary Risks of Large Language Models

Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less attention has been given to non-adversarial failures that...

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...

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 ...

CnC-PRAC: Coalesce, Not Cache, Per Row Activation Counts for an Efficient In-DRAM Rowhammer Mitigation

JEDEC has introduced the Per Row Activation Counting PRAC framework for DDR5 and future DRAMs to enable precise counting of DRAM row activations using per-row activation counts. While recent PRAC implementations enable holistic mitigation of Rowhammer attacks, they impose slowdowns of up to 10% d...

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models

Vision-Language Models VLMs such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable to adversarial attacks, particularly in the image modality,...

A Retrospective on DISPEED -- Leveraging Heterogeneity in a Drone Swarm for IDS Execution

Swarms of drones are gaining more and more autonomy and efficiency during their missions. However, security threats can disrupt their missions' progression. To overcome this problem, Network Intrusion Detection Systems NIDS are promising solutions to detect malicious behavior on network traffic...

GNSS Spoofing Detection Based on Opportunistic Position Information

The limited or no protection for civilian Global Navigation Satellite System GNSS signals makes spoofing attacks relatively easy. With modern mobile devices often featuring network interfaces, state-of-the-art signals of opportunity SOP schemes can provide accurate network positions in replacemen...