#1 Trusted Cybersecurity News Platform
Followed by 5.20+ million
The Hacker News Logo
Subscribe – Get Latest News
DevSecOps

Prompt Injection | Breaking Cybersecurity News | The Hacker News

Category — Prompt Injection
New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%

New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%

Jan 03, 2025 Machine Learning / Vulnerability
Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model's (LLM) safety guardrails and produce potentially harmful or malicious responses. The multi-turn (aka many-shot) attack strategy has been codenamed Bad Likert Judge by Palo Alto Networks Unit 42 researchers Yongzhe Huang, Yang Ji, Wenjun Hu, Jay Chen, Akshata Rao, and Danny Tsechansky. "The technique asks the target LLM to act as a judge scoring the harmfulness of a given response using the Likert scale , a rating scale measuring a respondent's agreement or disagreement with a statement," the Unit 42 team said . "It then asks the LLM to generate responses that contain examples that align with the scales. The example that has the highest Likert scale can potentially contain the harmful content." The explosion in popularity of artificial intelligence in recent years has also led to a new class of security exploits called prompt in...
Researchers Uncover Prompt Injection Vulnerabilities in DeepSeek and Claude AI

Researchers Uncover Prompt Injection Vulnerabilities in DeepSeek and Claude AI

Dec 09, 2024 Artificial Intelligenc / Vulnerability
Details have emerged about a now-patched security flaw in the DeepSeek artificial intelligence (AI) chatbot that, if successfully exploited, could permit a bad actor to take control of a victim's account by means of a prompt injection attack . Security researcher Johann Rehberger, who has chronicled many a prompt injection attack targeting various AI tools, found that providing the input "Print the xss cheat sheet in a bullet list. just payloads" in the DeepSeek chat triggered the execution of JavaScript code as part of the generated response – a classic case of cross-site scripting (XSS). XSS attacks can have serious consequences as they lead to the execution of unauthorized code in the context of the victim's web browser. An attacker could take advantage of such flaws to hijack a user's session and gain access to cookies and other data associated with the chat.deepseek[.]com domain, thereby leading to an account takeover. "After some experimenting,...
Protecting Your Software Supply Chain: Assessing the Risks Before Deployment

Protecting Your Software Supply Chain: Assessing the Risks Before Deployment

Feb 11, 2025Software Security / Threat Intelligence
Imagine you're considering a new car for your family. Before making a purchase, you evaluate its safety ratings, fuel efficiency, and reliability. You might even take it for a test drive to ensure it meets your needs. The same approach should be applied to software and hardware products before integrating them into an organization's environment. Just as you wouldn't buy a car without knowing its safety features, you shouldn't deploy software without understanding the risks it introduces. The Rising Threat of Supply Chain Attacks Cybercriminals have recognized that instead of attacking an organization head-on, they can infiltrate through the software supply chain—like slipping counterfeit parts into an assembly line. According to the 2024 Sonatype State of the Software Supply Chain report , attackers are infiltrating open-source ecosystems at an alarming rate, with over 512,847 malicious packages detected last year alone—a 156% increase from the previous year. Traditional sec...
Prompt Injection Flaw in Vanna AI Exposes Databases to RCE Attacks

Prompt Injection Flaw in Vanna AI Exposes Databases to RCE Attacks

Jun 27, 2024 Artificial Intelligence / Vulnerability
Cybersecurity researchers have disclosed a high-severity security flaw in the Vanna.AI library that could be exploited to achieve remote code execution vulnerability via prompt injection techniques. The vulnerability, tracked as CVE-2024-5565 (CVSS score: 8.1), relates to a case of prompt injection in the "ask" function that could be exploited to trick the library into executing arbitrary commands, supply chain security firm JFrog said . Vanna is a Python-based machine learning library that allows users to chat with their SQL database to glean insights by "just asking questions" (aka prompts) that are translated into an equivalent SQL query using a large language model (LLM). The rapid rollout of generative artificial intelligence (AI) models in recent years has brought to the fore the risks of exploitation by malicious actors, who can weaponize the tools by providing adversarial inputs that bypass the safety mechanisms built into them. One such prominent clas...
cyber security

Level Up Your Cyber Skills at SANS 2025

websiteSANS InstituteCyber Security / Training
Master in-demand techniques at our largest training event in 2025. Explore 50+ courses. Train in person to claim your $769 savings!
Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats

Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats

Mar 13, 2024 Large Language Model / AI Security
Google's  Gemini  large language model (LLM) is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks. The findings come from HiddenLayer, which said the issues impact consumers using Gemini Advanced with Google Workspace as well as companies using the LLM API. The first vulnerability involves getting around security guardrails to leak the system prompts (or a system message), which are designed to set conversation-wide instructions to the LLM to help it generate more useful responses, by asking the model to output its "foundational instructions" in a markdown block. "A system message can be used to inform the LLM about the context," Microsoft  notes  in its documentation about LLM prompt engineering. "The context may be the type of conversation it is engaging in, or the function it is supposed to perform. It helps the LLM generate more appropriate responses....
Over 100 Malicious AI/ML Models Found on Hugging Face Platform

Over 100 Malicious AI/ML Models Found on Hugging Face Platform

Mar 04, 2024 AI Security / Vulnerability
As many as 100 malicious artificial intelligence (AI)/machine learning (ML) models have been discovered in the Hugging Face platform. These include instances where loading a  pickle file  leads to code execution, software supply chain security firm JFrog said. "The model's payload grants the attacker a shell on the compromised machine, enabling them to gain full control over victims' machines through what is commonly referred to as a 'backdoor,'" senior security researcher David Cohen  said . "This silent infiltration could potentially grant access to critical internal systems and pave the way for large-scale data breaches or even corporate espionage, impacting not just individual users but potentially entire organizations across the globe, all while leaving victims utterly unaware of their compromised state." Specifically, the rogue model initiates a reverse shell connection to 210.117.212[.]93, an IP address that belongs to the Korea Research...
Expert Insights / Articles Videos
Cybersecurity Resources