Hackers can use 9 of the most popular AI tools to assemble massive botnets

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...
JD Supra

The Intellectual Property Behind the Soccer World Cup: How to Avoid Offsides When Securing IP “Goals”

As the 2026 FIFA World Cup unfolds across North America, the world is focused on the players, coaches, and dramatic moments on the field.
IEEE

Adversarial Computer Vision via Acoustic Manipulation of Camera Sensors

Abstract: Autonomous vehicles increasingly rely on camera-based computer vision systems to perceive environments and make critical driving decisions. To improve image quality, image stabilizers with ...
IEEE

On the Adversarial Robustness of Hand-Crafted Features and Their Role in Defending Adversarial Examples

Abstract: Deep Neural Networks (DNNs) have achieved tremendous success in various computer vision tasks but remain highly vulnerable to adversarial examples. To address this limitation, we investigate ...
GitHub

Official Pytorch implementation for "Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization" (CVPR 2023).

ViT models are all available in timm library. We consider four surrogate models (vit_base_patch16_224, pit_b_224, cait_s24_224, and visformer_small) and four additional target models ...
PNAS

Prevalence of simplex compression in adversarial deep neural networks

Despite the widespread success of neural networks, their susceptibility to adversarial examples remains a significant challenge. Adversarial training (AT) has emerged as an effective approach to ...
scienceopen.com

AF2-mutation: adversarial sequence mutations against AlphaFold2 in protein tertiary structure prediction

Proteins are essential macromolecules that perform functions according to their conformational dynamics. Studying the conformational changes induced by protein mutations is the standard approach used ...
Frontiers

Manifold-driven decomposition for adversarial robustness

The adversarial risk of a machine learning model has been widely studied. Most previous studies assume that the data lie in the whole ambient space. We propose to take a new angle and take the ...
Royal Institution

10 AI milestones of the last 10 years

When ChatGPT-3 crash-landed onto our computers in November 2022, you’d have been forgiven for thinking this massive leap in artificial intelligence had sprung out of nowhere. From one day to the next, ...
Forbes

Adversarial Attacks On AI Systems

We are witnessing a rapid advancement of AI and its impact across various industries. However, with great power comes great responsibility, and one of the emerging challenges in the AI landscape is ...
Frontiers

Adversarial attacks on spiking convolutional neural networks for event-based vision

Event-based dynamic vision sensors provide very sparse output in the form of spikes, which makes them suitable for low-power applications. Convolutional spiking neural networks model such event-based ...