Related papers: Malicious Agent Detection for Robust Multi-Agent C…

In recent years, neural networks have become the default choice for image classification and many other learning tasks, even though they are vulnerable to so-called adversarial attacks. To increase their robustness against these attacks,…

End-to-end encryption (E2EE) by messaging platforms enable people to securely and privately communicate with one another. Its widespread adoption however raised concerns that illegal content might now be shared undetected. Following the…

The multi-agent perception system collects visual data from sensors located on various agents and leverages their relative poses determined by GPS signals to effectively fuse information, mitigating the limitations of single-agent sensing,…

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…

Collaborative autonomous driving with multiple vehicles usually requires the data fusion from multiple modalities. To ensure effective fusion, the data from each individual modality shall maintain a reasonably high quality. However, in…

Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often underperform in few-shot settings and remain vulnerable to adversarial, humanizing attacks. To build accurate and…

Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns…

Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face forensics can…

We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous internal mechanisms. Mechanistic anomaly detection (MAD) aims…

Nowadays, intrusion detection systems based on deep learning deliver state-of-the-art performance. However, recent research has shown that specially crafted perturbations, called adversarial examples, are capable of significantly reducing…

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

We consider an echo-assisted communication model wherein block-coded messages, when transmitted across several frames, reach the destination as multiple noisy copies. We address adversarial attacks on such models wherein a subset of the…

Adversarial attacks pose a severe risk to AI systems used in healthcare, capable of misleading models into dangerous misclassifications that can delay treatments or cause misdiagnoses. These attacks, often imperceptible to human perception,…

Autonomous agents are increasingly deployed in both offensive and defensive cyber operations, creating high-speed, closed-loop interactions in critical infrastructure environments. Advanced Persistent Threat (APT) actors exploit "Living off…

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g.,…

Collaborative perception allows each agent to enhance its perceptual abilities by exchanging messages with others. It inherently results in a trade-off between perception ability and communication costs. Previous works transmit complete…

Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against…

We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating…

Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…