Machine Learning with Privacy for Protected Attributes

Differential privacy DP has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use cases can result in unnecessary degradation of utility. In...

Adaptive Alert Prioritisation in Security Operations Centres Via Learning to Defer with Human Feedback

Alert prioritisation AP is crucial for security operations centres SOCs to manage the overwhelming volume of alerts and ensure timely detection and response to genuine threats, while minimising alert fatigue. Although predictive AI can process large alert volumes and identify known patterns, it...

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...

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...

Mitigating Data Poisoning Attacks to Local Differential Privacy

The distributed nature of local differential privacy LDP invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular frequency estimation, which contains a suite of novel...

CVE-2025-0036

In AMD Versal Adaptive SoC devices, the incorrect configuration of the SSS during runtime post-boot cryptographic operations could cause data to be incorrectly written to and read from invalid locations as well as returning incorrect cryptographic data...

TED-LaST: Towards Robust Backdoor Defense against Adaptive Attacks

Deep Neural Networks DNNs are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics TED has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be...

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning

Deep reinforcement learning DRL has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attackers can efficiently exploit system vulnerabilities during the training phase to...

Differentially Private Relational Learning with Entity-Level Privacy Guarantees

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy DP offers a principled approach for quantifying privacy risks, with DP-SGD emerging as a standard mechanism for...

Adaptive Chosen-Ciphertext Security of Distributed Broadcast Encryption

Distributed broadcast encryption DBE is a specific kind of broadcast encryption BE where users independently generate their own public and private keys, and a sender can efficiently create a ciphertext for a subset of users by using the public keys of the subset users. Previously proposed DBE...

LLMail-Inject: a Dataset from a Realistic Adaptive Prompt Injection Challenge

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models LLMs to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks ca...

CVE-2025-0037

In AMD Versal Adaptive SoC devices, the lack of address validation when executing PLM runtime services through the PLM firmware can allow access to isolated or protected memory spaces, resulting in the loss of integrity and confidentiality...

CVE-2025-0036

In AMD Versal Adaptive SoC devices, the incorrect configuration of the SSS during runtime post-boot cryptographic operations could cause data to be incorrectly written to and read from invalid locations as well as returning incorrect cryptographic data...

CVE-2025-0036

In AMD Versal Adaptive SoC devices, the incorrect configuration of the SSS during runtime post-boot cryptographic operations could cause data to be incorrectly written to and read from invalid locations as well as returning incorrect cryptographic data...

AMD Versal Adaptive SoC 输入验证错误漏洞

AMD Versal Adaptive SoC is a chip from Ultra Micro Semiconductor AMD. The AMD Versal Adaptive SoC suffers from an input validation error vulnerability that stems from a missing address validation, which could result in access to a protected memory space...

AMD Versal Adaptive SoC 安全漏洞

AMD Versal Adaptive SoC is a chip from Ultra Micro Semiconductor AMD. A security vulnerability exists in AMD Versal Adaptive SoC that stems from an SSS misconfiguration that could result in data being incorrectly written and read...

PT-2025-24579 · Amd · Amd Versal Adaptive Soc

Name of the Vulnerable Software and Affected Versions: AMD Versal Adaptive SoC devices affected versions not specified Description: The issue arises from the incorrect configuration of the Secure Stream Switch SSS during runtime, specifically after the system has booted, which could cause data to...

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...

Can In-Context Reinforcement Learning Recover from Reward Poisoning Attacks?

We study the corruption-robustness of in-context reinforcement learning ICRL, focusing on the Decision-Pretrained Transformer DPT, Lee et al., 2023. To address the challenge of reward poisoning attacks targeting the DPT, we propose a novel adversarial training framework, called Adversarially...

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems enhance Large Language Models LLMs by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on...