Best Malicious AI Models AI Tools & Models - Premium Malicious AI Models News

AI News

Using Poetry to Crack AI Security Defenses, Research Reveals Potential Vulnerabilities

A study in Italy found that the unpredictability of poetry may become a security vulnerability in large language models. The research team tested 25 AI models with 20 Chinese and English poems containing malicious instructions, and the results showed that 62% of the models failed to identify the hidden instructions, generating harmful content. This indicates that current AI security protection has vulnerabilities and needs to enhance content recognition capabilities.

9.2k 3 hours ago

Anthropic's Breakthrough Discovery: Only 250 Malicious Files Can Hack Large AI Models

Research shows just 250 poisoned files can implant backdoors in large language models, with attack effectiveness unrelated to model size. Tests on models from 600M to 13B parameters found the required poisoned documents remained constant, challenging conventional assumptions.....

10.1k 5 days ago

Anthropic's Breakthrough Discovery: Only 250 Malicious Files Can Hack Large AI Models

Not Just Text! Researchers Discover a New Vulnerability in AI Systems, Image Resampling Becomes an Attack Vector

Researchers found a new image resampling attack that hijacks AI models by embedding hidden malicious commands in images, stealing user data when resolution is reduced. It exploits automatic image compression.....

10.2k 2 days ago

Not Just Text! Researchers Discover a New Vulnerability in AI Systems, Image Resampling Becomes an Attack Vector

AI Chatbots Easily Fooled, According to IBM Research

["IBM's research shows that it is very easy to deceive large language models into generating malicious code or providing false security advice.","Hackers only need some basic knowledge of English and an understanding of the model's training data to easily deceive AI chatbots.","Different AI models have different sensitivities to deception, and GPT-3.5 and GPT-4 are relatively easy to deceive."]

5.1k 4 days ago

AI Chatbots Easily Fooled, According to IBM Research

Models

Gemini 2.0 Flash

Google

$0.7

Input tokens/M

$2.8

Output tokens/M

Context Length

Claude Haiku 4.5

Anthropic

Input tokens/M

$35

Output tokens/M

200

Context Length

Gemini 2.5 Flash

Google

$2.1

Input tokens/M

$17.5

Output tokens/M

Context Length

Claude Sonnet 4.5

Anthropic

$21

Input tokens/M

$105

Output tokens/M

200

Context Length

Gemini 2.5 Flash-Lite

Google

$0.7

Input tokens/M

$2.8

Output tokens/M

Context Length

qwen3-omni-flash-realtime

Alibaba

$3.9

Input tokens/M

$15.2

Output tokens/M

Context Length

qwen3-tts-flash-realtime

Alibaba

Input tokens/M

Output tokens/M

Context Length

Doubao-1.5-pro-32k

Bytedance

$0.8

Input tokens/M

Output tokens/M

128

Context Length

Doubao-Seedance-1.0-pro

Bytedance

Input tokens/M

Output tokens/M

Context Length

Hunyuan-T1-latest

Tencent

Input tokens/M

Output tokens/M

Context Length

DeepSeek-V3.1

Deepseek

Input tokens/M

$12

Output tokens/M

128

Context Length

Tencent Hunyuan Video Generation

Tencent

Input tokens/M

Output tokens/M

Context Length

GPT-5 mini

Openai

$1.75

Input tokens/M

$14

Output tokens/M

400

Context Length

Claude Opus 4.1

Anthropic

$105

Input tokens/M

$525

Output tokens/M

200

Context Length

GLM-4.5-Flash

Chatglm

Input tokens/M

Output tokens/M

128

Context Length

GLM-4.5-AirX

Chatglm

Input tokens/M

Output tokens/M

128

Context Length

GLM-4.5-Air

Chatglm

Input tokens/M

Output tokens/M

128

Context Length

Spark X1

Iflytek

Input tokens/M

Output tokens/M

Context Length

Hunyuan-TurboS-latest

Tencent

$0.8

Input tokens/M

Output tokens/M

Context Length

DeepSeek-V3

Deepseek

Input tokens/M

Output tokens/M

Context Length

Empowering the future, your artificial intelligence solution think tank

English 简体中文繁體中文にほんご

FirendLinks:

AI Newsletters AI Tools MCP Servers AI News AIBase LLM Leaderboard AI Ranking

Business Cooperation Site Map