Utah Rep. Blake Moore is co-leading a push to crack down on foreign nationals abusing U.S. surrogacy services in an effort to ...

Artificial intelligence (AI) safety has turned into a constant cat-and-mouse game. As developers add guardrails to block harmful requests, attackers continue to try new ways to circumvent them. One of ...

Riddle-like poems tricked chatbots into spewing hate speech and helping design nuclear weapons and nerve agents. Riddle-like poems tricked chatbots into spewing hate speech and helping design nuclear ...

This repository contains the implementation of topological data analysis (TDA) methods for detecting adversarial examples in deep learning models, particularly focusing on Vision-Language models like ...

Trump Cyber Team Wants to 'Shape Adversary Behavior.' Allies Are Skeptical Bad actors need to know their actions have consequences, National Cyber Director Sean Cairncross says at a conference that ...

Stop me if you've heard this one before: xAI is once again nuking a bunch of posts from Grok on X after the chatbot made a series of outrageous claims. This time, though, the company isn't cleaning up ...

Artificial intelligence (AI) systems can be fooled by certain image inputs. Called adversarial examples, they incorporate subtle changes to a picture that are imperceptible to humans and can be ...

1 College of Electronic Engineering, National University of Defense Technology, Hefei, Anhui, China 2 Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation, Hefei, ...

Co-founded by former MITRE experts, the startup will use the funding to accelerate product innovation and fuel company growth. Cybersecurity provider Tidal Cyber on Wednesday announced raising $10 ...

New vulnerabilities have emerged with the rapid advancement and adoption of multimodal foundational AI models, significantly expanding the potential for cybersecurity attacks. Researchers at Los ...

The emergence of both task-specific single-modality models and general-purpose multimodal large models presents new opportunities, but also introduces challenges, particularly regarding adversarial ...