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...

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...

RAS-Eval: a Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments

The rapid deployment of Large language model LLM agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standardized evaluation benchmarks for these agents in dynamic environments, we introduce RAS-Eval, a comprehensive security...

Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing

In the semiconductor sector, due to high demand but also strong and increasing competition, time to market and quality are key factors in securing significant market share in various application areas. Thanks to the success of deep learning methods in recent years in the computer vision domain,...

Understanding Content Moderation Policies and User Experiences in Generative AI Products

While recent research has focused on developing safeguards for generative AI GAI model-level content safety, little is known about how content moderation to prevent malicious content performs for end-users in real-world GAI products. To bridge this gap, we investigated content moderation policies...

Unlearning-Enhanced Website Fingerprinting Attack: against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting WF is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website...

Towards Effective Complementary Security Analysis Using Large Language Models

A key challenge in security analysis is the manual evaluation of potential security weaknesses generated by static application security testing SAST tools. Numerous false positives FPs in these reports reduce the effectiveness of security analysis. We propose using Large Language Models LLMs to...

From Thinking to Output: Chain-Of-Thought and Text Generation Characteristics in Reasoning Language Models

Recently, there have been notable advancements in large language models LLMs, demonstrating their growing abilities in complex reasoning. However, existing research largely overlooks a thorough and systematic comparison of these models' reasoning processes and outputs, particularly regarding thei...

SAFER-D: a Self-Adaptive Security Framework for Distributed Computing Architectures

The rise of the Internet of Things and Cyber-Physical Systems has introduced new challenges on ensuring secure and robust communication. The growing number of connected devices increases network complexity, leading to higher latency and traffic. Distributed computing architectures DCAs have gaine...

Malicious code in world-id-js (npm)

--- -= Per source details. Do not edit below this line.=-...

AgentVigil: Generic Black-Box Red-Teaming for Indirect Prompt Injection against LLM Agents

The strong planning and reasoning capabilities of Large Language Models LLMs have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these powerful features also introduce a critical security risk:...

MAYA: Addressing Inconsistencies in Generative Password Guessing through a Unified Benchmark

Recent advances in generative models have led to their application in password guessing, with the aim of replicating the complexity, structure, and patterns of human-created passwords. Despite their potential, inconsistencies and inadequate evaluation methodologies in prior research have hindered...

LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

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...

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 Certified Unlearning Approach without Access to Source Data

With the growing adoption of data privacy regulations, the ability to erase private or copyrighted information from trained models has become a crucial requirement. Traditional unlearning methods often assume access to the complete training dataset, which is unrealistic in scenarios where the...

Malicious code in world-id-lens-dapp (npm)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis d27d63976b7108297f8d9a29062b3add9973c83849fd5ab7cd8fbd31b0248701 The OpenSSF Package Analysis project identified 'world-id-lens-dapp' @ 1.0.0 npm as malicious. It is considered malicious because: - The package...

MAL-2025-4670 Malicious code in world-id-lens-dapp (npm)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis d27d63976b7108297f8d9a29062b3add9973c83849fd5ab7cd8fbd31b0248701 The OpenSSF Package Analysis project identified 'world-id-lens-dapp' @ 1.0.0 npm as malicious. It is considered malicious because: - The package...

Malicious code in world-id-poap (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis bdb64432a67fa7109c5ee4d1d5b94d0127eaedab876302eb3b246ae55b111498 The OpenSSF Package Analysis project identified 'world-id-poap' @ 1.0...

MAL-2025-4669 Malicious code in world-id-poap (npm)

The package communicates with a domain associated with malicious activity. --- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis bdb64432a67fa7109c5ee4d1d5b94d0127eaedab876302eb3b246ae55b111498 The OpenSSF Package Analysis project identified 'world-id-poap' @ 1.0...