Defensa y seguridad

Defending Quantum Classifiers against Adversarial Perturbations through Quantum Autoencoders

- Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can...

Formulating Subgroup Discovery as a Quantum Optimization Problem for Network Security

- While current network intrusion detection systems achieve satisfactory accuracy, they often lack explainability. Subgroup Discovery (SD) addresses this by building interpretable rules that...

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

- Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents,...

Unsafe and Unused? A History of Utility Code in Mature Open Source Projects

- Filenames are a concise means of conveying information about source code to fellow developers. One such convention is util. Commonly understood to stand for "utility", filenames with the...

Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection

- Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack...

Splitting Argumentation Frameworks with Collective Attacks and Supports

- This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies on bipolar set-based argumentation frameworks...

Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge

- Current DeepFake detection scenarios are mostly binary, yet data manipulation can vary across audio, video, or both, whose variability is not captured in binary settings. Four-class audio-visual...

Splitting Assumption-Based Argumentation Frameworks

- Assumption-Based Argumentation (ABA) is a well-established formalism for modelling and reasoning over debates, with a wide range of applications. However, the high computational complexity of core...

Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing

- Large-scale IoT weather sensing networks require incentive mechanisms to sustain participation, yet determining how much value individual data contributions bring to the network remains an open...

Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs

- Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade...

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning

- Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that...

Requirements Debt in AI-Enabled Perception Systems Development: An Industrial RE4AI Perspective

- AI integration in automotive perception systems shifts requirements from static specifications to continuously evolving entities shaped by data, models, and operating contexts. When such changes are...

Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning

- Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but directly sharing them poses privacy risks. A common...

Hybrid Anomaly Detection for Bullion Coin Authentication Leveraging Acoustic Signature Analysis

- The verification of bullion coin authenticity is essential for maintaining integrity within the precious metals market; however, the increasing sophistication of counterfeits has rendered traditional...

How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection

- How code representation format shapes false positive behaviour in cross-language LLM vulnerability detection remains poorly understood. We systematically vary training intensity and code...

PuzzleMark: Implicit Jigsaw Learning for Robust Code Dataset Watermarking in Neural Code Completion Models

- Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of...

One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness

- The hubness problem, in which hub embeddings are close to many unrelated examples, occurs often in high-dimensional embedding spaces and may pose a practical threat for purposes such as information...

VOW: Verifiable and Oblivious Watermark Detection for Large Language Models

- Large Language Model (LLM) watermarking is crucial for establishing the provenance of machine-generated text, but most existing methods rely on a centralized trust model. This model forces users to...

Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling

- Protecting sensitive health data while enabling collaborative analysis is a central challenge in healthcare. Traditional machine learning (ML) requires institutions to pool anonymized patient...

Learning from a single labeled face and a stream of unlabeled data

- Face recognition from a single image per person is a challenging problem because the training sample is extremely small. We consider a variation of this problem. In our problem, we recognize only one...

Low Rank Adaptation for Adversarial Perturbation

- Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models...