相关论文: Automated Adversarial Discovery for Safety Classif…

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in…

As the AI systems become deeply embedded in social media platforms, we've uncovered a concerning security vulnerability that goes beyond traditional adversarial attacks. It becomes important to assess the risks of LLMs before the general…

The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same…

Large Language Models (LLMs) have become vital tools in software development tasks such as code generation, completion, and analysis. As their integration into workflows deepens, ensuring robustness against vulnerabilities especially those…

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed…

Online fake news profoundly distorts public judgment and erodes trust in social platforms. While existing detectors achieve competitive performance on benchmark datasets, they remain notably vulnerable to malicious comments designed…

Learning-based pattern classifiers, including deep networks, have shown impressive performance in several application domains, ranging from computer vision to cybersecurity. However, it has also been shown that adversarial input…

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security against well-crafted attacks that aim to evade detection by…

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Deep neural networks have demonstrated remarkable effectiveness across a wide range of tasks such as semantic segmentation. Nevertheless, these networks are vulnerable to adversarial attacks that add imperceptible perturbations to the input…

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…

The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues. For many safety-critical ML tasks, such as financial forecasting, fraudulent detection, and anomaly…

Better methods to detect insider threats need new anticipatory analytics to capture risky behavior prior to losing data. In search of the best overall classifier, this work empirically scores 88 machine learning algorithms in 16 major…

Toxicity detection is crucial for maintaining the peace of the society. While existing methods perform well on normal toxic contents or those generated by specific perturbation methods, they are vulnerable to evolving perturbation patterns.…

An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…

The research field of adversarial machine learning witnessed a significant interest in the last few years. A machine learner or model is secure if it can deliver main objectives with acceptable accuracy, efficiency, etc. while at the same…

Completely Automated Public Turing test to tell Computers and Humans Apart, short for CAPTCHA, is an essential and relatively easy way to defend against malicious attacks implemented by bots. The security and usability trade-off limits the…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more…

Many word-level adversarial attack approaches for textual data have been proposed in recent studies. However, due to the massive search space consisting of combinations of candidate words, the existing approaches face the problem of…