Speaker Anonymisation for Speech-based Suicide Risk Detection

Adolescent suicide is a critical global health issue, and speech provides a cost-effective modality for automatic suicide risk detection. Given the vulnerable population, protecting speaker identity is particularly important, as speech itself can reveal personally identifiable information if the data is leaked or maliciously exploited. This work presents the first systematic study of speaker anonymisation for speech-based suicide risk detection. A broad range of anonymisation methods are investigated, including techniques based on traditional signal processing, neural voice conversion, and speech synthesis. A comprehensive evaluation framework is built to assess the trade-off between protecting speaker identity and preserving information essential for suicide risk detection. Results show that combining anonymisation methods that retain complementary information yields detection performance comparable to that of original speech, while achieving protection of speaker identity for vulnerable populations.

SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios

Large language model (LLM) powered code agents are rapidly transforming software engineering by automating tasks such as testing, debugging, and repairing, yet the security risks of their generated code have become a critical concern. Existing benchmarks have offered valuable insights but remain insufficient: they often overlook the genuine context in which vulnerabilities were introduced or adopt narrow evaluation protocols that fail to capture either functional correctness or newly introduced vulnerabilities. We therefore introduce SecureAgentBench, a benchmark of 105 coding tasks designed to rigorously evaluate code agents' capabilities in secure code generation. Each task includes (i) realistic task settings that require multi-file edits in large repositories, (ii) aligned contexts based on real-world open-source vulnerabilities with precisely identified introduction points, and (iii) comprehensive evaluation that combines functionality testing, vulnerability checking through proof-of-concept exploits, and detection of newly introduced vulnerabilities using static analysis. We evaluate three representative agents (SWE-agent, OpenHands, and Aider) with three state-of-the-art LLMs (Claude 3.7 Sonnet, GPT-4.1, and DeepSeek-V3.1). Results show that (i) current agents struggle to produce secure code, as even the best-performing one, SWE-agent supported by DeepSeek-V3.1, achieves merely 15.2% correct-and-secure solutions, (ii) some agents produce functionally correct code but still introduce vulnerabilities, including new ones not previously recorded, and (iii) adding explicit security instructions for agents does not significantly improve secure coding, underscoring the need for further research. These findings establish SecureAgentBench as a rigorous benchmark for secure code generation and a step toward more reliable software development with LLMs.

Validating Solidity Code Defects using Symbolic and Concrete Execution powered by Large Language Models

The high rate of false alarms from static analysis tools and Large Language Models (LLMs) complicates vulnerability detection in Solidity Smart Contracts, demanding methods that can formally or empirically prove the presence of defects. This paper introduces a novel detection pipeline that integrates custom Slither-based detectors, LLMs, Kontrol, and Forge. Our approach is designed to reliably detect defects and generate proofs. We currently perform experiments with promising results for seven types of critical defects. We demonstrate the pipeline's efficacy by presenting our findings for three vulnerabilities -- Reentrancy, Complex Fallback, and Faulty Access Control Policies -- that are challenging for current verification solutions, which often generate false alarms or fail to detect them entirely. We highlight the potential of either symbolic or concrete execution in correctly classifying such code faults. By chaining these instruments, our method effectively validates true positives, significantly reducing the manual verification burden. Although we identify potential limitations, such as the inconsistency and the cost of LLMs, our findings establish a robust framework for combining heuristic analysis with formal verification to achieve more reliable and automated smart contract auditing.

Watermarking and Anomaly Detection in Machine Learning Models for LORA RF Fingerprinting

Radio frequency fingerprint identification (RFFI) distinguishes wireless devices by the small variations in their analog circuits, avoiding heavy cryptographic authentication. While deep learning on spectrograms improves accuracy, models remain vulnerable to copying, tampering, and evasion. We present a stronger RFFI system combining watermarking for ownership proof and anomaly detection for spotting suspicious inputs. Using a ResNet-34 on log-Mel spectrograms, we embed three watermarks: a simple trigger, an adversarially trained trigger robust to noise and filtering, and a hidden gradient/weight signature. A convolutional Variational Autoencoders (VAE) with Kullback-Leibler (KL) warm-up and free-bits flags off-distribution queries. On the LoRa dataset, our system achieves 94.6% accuracy, 98% watermark success, and 0.94 AUROC, offering verifiable, tamper-resistant authentication.

Deceptive Beauty: Evaluating the Impact of Beauty Filters on Deepfake and Morphing Attack Detection

Digital beautification through social media filters has become increasingly popular, raising concerns about the reliability of facial images and videos and the effectiveness of automated face analysis. This issue is particularly critical for digital manipulation detectors, systems aiming at distinguishing between genuine and manipulated data, especially in cases involving deepfakes and morphing attacks designed to deceive humans and automated facial recognition. This study examines whether beauty filters impact the performance of deepfake and morphing attack detectors. We perform a comprehensive analysis, evaluating multiple state-of-the-art detectors on benchmark datasets before and after applying various smoothing filters. Our findings reveal performance degradation, highlighting vulnerabilities introduced by facial enhancements and underscoring the need for robust detection models resilient to such alterations.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which are usually trained on text produced by humans, suffer from misclassifications due to LLM-generated text deviating from their training data and adversarial attacks that aim to avoid detection. Present-day defence tactics are reactive rather than proactive, since they rely on adversarial training or external detection models to identify attacks. In this work, we aim to identify the vulnerable components of toxicity classifiers that contribute to misclassification, proposing a novel strategy based on mechanistic interpretability techniques. Our study focuses on fine-tuned BERT and RoBERTa classifiers, testing on diverse datasets spanning a variety of minority groups. We use adversarial attacking techniques to identify vulnerable circuits. Finally, we suppress these vulnerable circuits, improving performance against adversarial attacks. We also provide demographic-level insights into these vulnerable circuits, exposing fairness and robustness gaps in model training. We find that models have distinct heads that are either crucial for performance or vulnerable to attack and suppressing the vulnerable heads improves performance on adversarial input. We also find that different heads are responsible for vulnerability across different demographic groups, which can inform more inclusive development of toxicity detection models.

AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within the retrieval pipeline, beyond the LLM itself. While prior RAG attacks have exposed such vulnerabilities, they largely rely on manipulating user queries, which is often infeasible in practice due to fixed or protected user inputs. This narrow focus overlooks a more realistic and stealthy vector: instructional prompts, which are widely reused, publicly shared, and rarely audited. Their implicit trust makes them a compelling target for adversaries to manipulate RAG behavior covertly. We introduce a novel attack for Adversarial Instructional Prompt (AIP) that exploits adversarial instructional prompts to manipulate RAG outputs by subtly altering retrieval behavior. By shifting the attack surface to the instructional prompts, AIP reveals how trusted yet seemingly benign interface components can be weaponized to degrade system integrity. The attack is crafted to achieve three goals: (1) naturalness, to evade user detection; (2) utility, to encourage use of prompts; and (3) robustness, to remain effective across diverse query variations. We propose a diverse query generation strategy that simulates realistic linguistic variation in user queries, enabling the discovery of prompts that generalize across paraphrases and rephrasings. Building on this, a genetic algorithm-based joint optimization is developed to evolve adversarial prompts by balancing attack success, clean-task utility, and stealthiness. Experimental results show that AIP achieves up to 95.23% ASR while preserving benign functionality. These findings uncover a critical and previously overlooked vulnerability in RAG systems, emphasizing the need to reassess the shared instructional prompts.

Recurrent Cross-View Object Geo-Localization

Cross-view object geo-localization (CVOGL) aims to determine the location of a specific object in high-resolution satellite imagery given a query image with a point prompt. Existing approaches treat CVOGL as a one-shot detection task, directly regressing object locations from cross-view information aggregation, but they are vulnerable to feature noise and lack mechanisms for error correction. In this paper, we propose ReCOT, a Recurrent Cross-view Object geo-localization Transformer, which reformulates CVOGL as a recurrent localization task. ReCOT introduces a set of learnable tokens that encode task-specific intent from the query image and prompt embeddings, and iteratively attend to the reference features to refine the predicted location. To enhance this recurrent process, we incorporate two complementary modules: (1) a SAM-based knowledge distillation strategy that transfers segmentation priors from the Segment Anything Model (SAM) to provide clearer semantic guidance without additional inference cost, and (2) a Reference Feature Enhancement Module (RFEM) that introduces a hierarchical attention to emphasize object-relevant regions in the reference features. Extensive experiments on standard CVOGL benchmarks demonstrate that ReCOT achieves state-of-the-art (SOTA) performance while reducing parameters by 60% compared to previous SOTA approaches.

JANUS: A Dual-Constraint Generative Framework for Stealthy Node Injection Attacks

Graph Neural Networks (GNNs) have demonstrated remarkable performance across various applications, yet they are vulnerable to sophisticated adversarial attacks, particularly node injection attacks. The success of such attacks heavily relies on their stealthiness, the ability to blend in with the original graph and evade detection. However, existing methods often achieve stealthiness by relying on indirect proxy metrics, lacking consideration for the fundamental characteristics of the injected content, or focusing only on imitating local structures, which leads to the problem of local myopia. To overcome these limitations, we propose a dual-constraint stealthy node injection framework, called Joint Alignment of Nodal and Universal Structures (JANUS). At the local level, we introduce a local feature manifold alignment strategy to achieve geometric consistency in the feature space. At the global level, we incorporate structured latent variables and maximize the mutual information with the generated structures, ensuring the injected structures are consistent with the semantic patterns of the original graph. We model the injection attack as a sequential decision process, which is optimized by a reinforcement learning agent. Experiments on multiple standard datasets demonstrate that the JANUS framework significantly outperforms existing methods in terms of both attack effectiveness and stealthiness.

On the Out-of-Distribution Backdoor Attack for Federated Learning

Traditional backdoor attacks in federated learning (FL) operate within constrained attack scenarios, as they depend on visible triggers and require physical modifications to the target object, which limits their practicality. To address this limitation, we introduce a novel backdoor attack prototype for FL called the out-of-distribution (OOD) backdoor attack ($\mathtt{OBA}$), which uses OOD data as both poisoned samples and triggers simultaneously. Our approach significantly broadens the scope of backdoor attack scenarios in FL. To improve the stealthiness of $\mathtt{OBA}$, we propose $\mathtt{SoDa}$, which regularizes both the magnitude and direction of malicious local models during local training, aligning them closely with their benign versions to evade detection. Empirical results demonstrate that $\mathtt{OBA}$ effectively circumvents state-of-the-art defenses while maintaining high accuracy on the main task. To address this security vulnerability in the FL system, we introduce $\mathtt{BNGuard}$, a new server-side defense method tailored against $\mathtt{SoDa}$. $\mathtt{BNGuard}$ leverages the observation that OOD data causes significant deviations in the running statistics of batch normalization layers. This allows $\mathtt{BNGuard}$ to identify malicious model updates and exclude them from aggregation, thereby enhancing the backdoor robustness of FL. Extensive experiments across various settings show the effectiveness of $\mathtt{BNGuard}$ on defending against $\mathtt{SoDa}$. The code is available at https://github.com/JiiahaoXU/SoDa-BNGuard.