Related papers: An oracle-based attack on CAPTCHAs protected again…
Image CAPTCHA, aiming at effectively distinguishing human users from malicious script attacks, has been an important mechanism to protect online systems from spams and abuses. Despite the increasing interests in developing and deploying…
Meta learning algorithms have been widely applied in many tasks for efficient learning, such as few-shot image classification and fast reinforcement learning. During meta training, the meta learner develops a common learning strategy, or…
Recently, we can observe a significant increase of the phishing attacks in the Internet. In a typical phishing attack, the attacker sets up a malicious website that looks similar to the legitimate website in order to obtain the end-users'…
Despite their advances and success, real-world deep neural networks are known to be vulnerable to adversarial attacks. Universal adversarial perturbation, an input-agnostic attack, poses a serious threat for them to be deployed in…
Deep neural networks have been widely used in many computer vision tasks. However, it is proved that they are susceptible to small, imperceptible perturbations added to the input. Inputs with elaborately designed perturbations that can fool…
Given the complexity of multi-tenant cloud environments and the growing need for real-time threat mitigation, Security Operations Centers (SOCs) must adopt AI-driven adaptive defense mechanisms to counter Advanced Persistent Threats (APTs).…
Text-based machine learning models are vulnerable to an emerging class of Unicode-based adversarial examples capable of tricking a model into misreading text with potentially disastrous effects. The primary existing defense against these…
The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise the performance of deep learning models by reducing output confidence or inducing…
Phishing is an increasingly sophisticated form of cyberattack that is inflicting huge financial damage to corporations throughout the globe while also jeopardizing individuals' privacy. Attackers are constantly devising new methods of…
In the not so unlikely scenario of total compromise of computers accessible to a group of users, they might be tempted to resort to human-computable paper-and-pencil cryptographic methods aided by a classic Tabula Recta, which helps to…
The ability to accurately predict cyber-attacks would enable organizations to mitigate their growing threat and avert the financial losses and disruptions they cause. But how predictable are cyber-attacks? Researchers have attempted to…
Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in unethical activities. Watermarking deters misuse by marking generated content with a hidden message, enabling its detection using a secret…
LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…
With the advancing digitization of our society, network security has become one of the critical concerns for most organizations. In this paper, we present CopAS, a system targeted at Big Data forensics analysis, allowing network operators…
This paper considers security risks buried in the data processing pipeline in common deep learning applications. Deep learning models usually assume a fixed scale for their training and input data. To allow deep learning applications to…
Standard Convolutional Neural Networks (CNNs) can be easily fooled by images with small quasi-imperceptible artificial perturbations. As alternatives to CNNs, the recently proposed Capsule Networks (CapsNets) are shown to be more robust to…
Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…
Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…
Learning from demonstrations is a popular approach to train AI models; however, their vulnerability to adversarial attacks remains underexplored. We present the first systematic study of adversarial attacks, across a range of both classic…
Since about 2003, captchas have been widely used as a barrier against bots, while simultaneously annoying great multitudes of users worldwide. As their use grew, techniques to defeat or bypass captchas kept improving, while captchas…