Practical Reasoning Interruption Attacks on Reasoning Large Language Models

Reasoning large language models RLLMs have demonstrated outstanding performance across a variety of tasks, yet they also expose numerous security vulnerabilities. Most of these vulnerabilities have centered on the generation of unsafe content. However, recent work has identified a distinct...

The Hidden Risks of LLM-Generated Web Application Code: a Security-Centric Evaluation of Code Generation Capabilities in Large Language Models

The rapid advancement of Large Language Models LLMs has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code generated by LLMs has been shown to generate insecure code in...

Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning Via Adaptive Token Compression

While reasoning large language models LLMs demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where model-generated reasoning tokens can forcibly interrupt th...

TookPS: DeepSeek isn’t the only game in town

In early March, we published a study detailing several malicious campaigns that exploited the popular DeepSeek LLM as a lure. Subsequent telemetry analysis indicated that the TookPS downloader, a malware strain detailed in the article, was not limited to mimicking neural networks. We identified...

DeepSeek users targeted with fake sponsored Google ads that deliver malware

The threat intel research used in this post was provided by Malwarebytes Senior Director of Research, Jérôme Segura. DeepSeek’s rising popularity has not only raised concerns and questions about privacy implications, but cybercriminals are also using it as a lure to trap unsuspecting Google...

AI Chatbot DeepSeek R1 Can Be Manipulated to Create Malware

Tenable Research reveals that AI chatbot DeepSeek R1 can be manipulated to generate keyloggers and ransomware code. While…...

Key Takeaways from the 2025 State of AI in the Cloud Report

From DeepSeek adoption to impact on security and governance...

Trojans disguised as AI: Cybercriminals exploit DeepSeek’s popularity

Introduction Among the most significant events in the AI world in early 2025 was the release of DeepSeek-R1 – a powerful reasoning large language model LLM with open weights. It's available both for local use and as a free service. Since DeepSeek was the first service to offer access to a reasoni...

Exploiting DeepSeek-R1: Breaking Down Chain of Thought Security

This entry explores how the Chain of Thought reasoning in the DeepSeek-R1 AI model can be susceptible to prompt attacks, insecure output generation, and sensitive data theft...

DeepSeek found to be sharing user data with TikTok parent company ByteDance

A couple of weeks ago we reported on the concerns surrounding data collection and security at DeepSeek, the Chinese AI company which recently made headlines for shaking up the industry after seemingly appearing from nowhere to become top of the app download charts. Now South Korea’s Personal...

Deepseek: Why it Matters and What the Press Got Wrong

...

South Korea Suspends DeepSeek AI Downloads Over Privacy Violations

South Korea has formally suspended new downloads of Chinese artificial intelligence AI chatbot DeepSeek in the country until the service makes changes to its mobile apps to comply with data protection regulations. Downloads have been paused as of February 15, 2025, 6:00 p.m. local time, the...

ChatGPT Finds XSS IN DeepSeek AI Python Code

ChatGPT finds cross site scripting issues with DeepSeek code examples. Let the AI fights begin! Summary: On 2025-02-09 ChatGPT AI found "security concern" XSS in DeepSeek's AI python code. Background: Consider the simple coding question Q: Write Python CGI which takes as an argument NAME and...

Hackers Monetize LLMjacking, Selling Stolen AI Access for $30 per Month

LLMjacking attacks target DeepSeek, racking up huge cloud costs. Sysdig reveals a black market for LLM access has…...

7,000 Exposed Ollama APIs Leave DeepSeek AI Models Wide Open to Attack

UpGuard discovers exposed Ollama APIs revealing DeepSeek model adoption globally. See where these AI models are running and the security risks involved...

Experts Flag Security, Privacy Risks in DeepSeek AI App

New mobile apps from the Chinese artificial intelligence AI company DeepSeek have remained among the top three "free" downloads for Apple and Google devices since their debut on Jan. 25, 2025. But experts caution that many of DeepSeek's design choices -- such as using hard-coded encryption keys,...

DeepSeek-R1 LLM Fails Over Half of Jailbreak Attacks in Security Analysis

DeepSeek-R1 LLM fails 58% of jailbreak attacks in Qualys security analysis. Learn about the vulnerabilities, compliance concerns, and risks for enterprise adoption...

Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks

Taiwan has become the latest country to ban government agencies from using Chinese startup DeepSeek's Artificial Intelligence AI platform, citing security risks. "Government agencies and critical infrastructure should not use DeepSeek, because it endangers national information security," accordin...

Hackers Hide Malware in Fake DeepSeek PyPI Packages

Malicious DeepSeek packages on PyPI spread malware, stealing sensitive data like API keys. Learn how this attack targeted developers and how to protect yourself...

Cisco Finds DeepSeek R1 Highly Vulnerable to Harmful Prompts

DeepSeek R1, a cost-efficient AI model, achieves impressive reasoning but fails all safety tests in a new study…...