Artificial Intelligence

SWARM – Switchable Backdoor Attack Against Pre-trained Models

In the big data era, pre-training large vision transformer (ViT) models on massive datasets has become prevalent for enhanced performance…

8 months ago

Hackers Moving To AI But Lacking Behind The Defenders In Adoption Rates

Hackers were actively exploiting the generative AI for cyber attacks; not only that, even threat actors are also exploring new…

9 months ago

GoldDigger Malware Using Deep Fake AI Photos To Hijack Bank Accounts

Hackers use deep fake AI photos to impersonate individuals online, allowing them to deceive, manipulate, or gain unauthorized access to…

9 months ago

Top Israeli Spy Chief Identity Exposed In A Privacy Mistake

Privacy mistakes could pose a serious threat to sensitive information or systems,, which threat actors could exploit for their gain.…

10 months ago

Chinese Hackers Using AI Tools To Influence Upcoming Elections

By exploiting the AI tools deepfake hackers could make videos or audios of political candidates to spread misinformation or disinformation,…

10 months ago

AI-As-A-Service Providers Vulnerability Let Attackers Perform Cross-Tenant Attacks

The fast acceptance of AI has serious security issues, as this necessitates strict security measures to be put in place…

10 months ago

Researchers Propose An Invisible Backdoor Attack Dubbed DEBA

As deep neural networks (DNNs) become more prevalent, concerns over their security against backdoor attacks that implant hidden malicious functionalities…

10 months ago

Researchers Hacked AI Assistants Using ASCII Art

Large language models (LLMs) are vulnerable to attacks, leveraging their inability to recognize prompts conveyed through ASCII art.  ASCII art…

11 months ago

Critical ChatGPT Plugins Flaw Let Attackers Gain Control Over Organization’s Account

Threat actors can exploit ChatGPT's ecosystem for several illicit purposes, such as crafting prompts to generate malicious code, phishing lures,…

11 months ago

BEAST AI Jailbreak Language Models Within 1 Minute With High Accuracy

Malicious hackers sometimes jailbreak language models (LMs) to exploit bugs in the systems so that they can perform a multitude…

11 months ago