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...

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...

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...

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...

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...

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...

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...

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...

Evaluation Pipeline for Systematically Searching for Anomaly Detection Systems

Digitalization in the medical world provides major benefits while making it a target for attackers and thus hard to secure. To deal with network intruders we propose an anomaly detection system on hardware to detect malicious clients in real-time. We meet real-time and power restrictions using...

From LLMs to MLLMs to Agents: a Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Large language models LLMs are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing increasingly severe security risks. This paper presents a systematic survey of the growing complexity of jailbreak...

Flexible Hardware-Enabled Guarantees for AI Compute

As artificial intelligence systems become increasingly powerful, they pose growing risks to international security, creating urgent coordination challenges that current governance approaches struggle to address without compromising sensitive information or national security. We propose flexible...

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain e.g., writing insecure code can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on...

Using LLMs for Security Advisory Investigations: How Far Are We?

Large Language Models LLMs are increasingly used in software security, but their trustworthiness in generating accurate vulnerability advisories remains uncertain. This study investigates the ability of ChatGPT to 1 generate plausible security advisories from CVE-IDs, 2 differentiate real from fa...

Position: Certified Robustness Does Not (Yet) Imply Model Security

While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We identify critical gaps in current research, including the parad...

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

The rapid advancement of large language models LLMs introduces dual-use capabilities that could both threaten and bolster national security and public safety NSPS. Models implement safeguards to protect against potential misuse relevant to NSPS and allow for benign users to receive helpful...

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning

Large Reasoning Models LRMs have demonstrated promising performance in complex tasks. However, the resource-consuming reasoning processes may be exploited by attackers to maliciously occupy the resources of the servers, leading to a crash, like the DDoS attack in cyber. To this end, we propose a...

Arbitrary Code Injection

Overview org.webjars.npm:jsonpath is a Query JavaScript objects with JSONPath expressions. Robust / safe JSONPath engine for Node.js. Affected versions of this package are vulnerable to Arbitrary Code Injection via unsafe evaluation of user-supplied JSON Path expressions. The library relies on th...

Arbitrary Code Injection

Overview jsonpath is a Query JavaScript objects with JSONPath expressions. Robust / safe JSONPath engine for Node.js. Affected versions of this package are vulnerable to Arbitrary Code Injection via unsafe evaluation of user-supplied JSON Path expressions. The library relies on the static-eval...

A Smart Contract-Based Non-Transferable Signature Verification System Using Nominative Signatures

Nominative signatures allow us to indicate who can verify a signature, and they can be employed to construct a non-transferable signature verification system that prevents the signature verification by a third party in unexpected situations. For example, this system can prevent IOU/loan certifica...

SafeGenBench: a Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code

The code generation capabilities of large language modelsLLMs have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code. In this work, we introduce SafeGenBench, a benchmark...