Search results for how can generative ai be poisoned | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have uncovered a jailbreak technique to bypass ethical guardrails erected by OpenAI in its latest large language model (LLM) GPT-5 and produce illicit instructions. Generative artificial intelligence (AI) security platform NeuralTrust said it combined a known technique called Echo Chamber with narrative-driven steering to trick the model into producing undesirable responses. "We use Echo Chamber to seed and reinforce a subtly poisonous conversational context, then guide the model with low-salience storytelling that avoids explicit intent signaling," security researcher Martí Jordà said . "This combination nudges the model toward the objective while minimizing triggerable refusal cues." Echo Chamber is a jailbreak approach that was detailed by the company back in June 2025 as a way to deceive an LLM into generating responses to prohibited topics using indirect references, semantic steering, and multi-step inference. In recent weeks, the...

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...

From unpatched cars to hijacked clouds, this week's Threatsday headlines remind us of one thing — no corner of technology is safe. Attackers are scanning firewalls for critical flaws, bending vulnerable SQL servers into powerful command centers, and even finding ways to poison Chrome's settings to sneak in malicious extensions. On the defense side, AI is stepping up to block ransomware in real time, but privacy fights over data access and surveillance are heating up just as fast. It's a week that shows how wide the battlefield has become — from the apps on our phones to the cars we drive. Don't keep this knowledge to yourself: share this bulletin to protect others, and add The Hacker News to your Google News list so you never miss the updates that could make the difference. Claude Now Finds Your Bugs Anthropic Touts Safety Protections Built Into Claude Sonnet 4.6 Anthropic said it has rolled out a number of safety and security improve...