defenders
Defenders turn the tables on AI hackers by using prompt injections to disable malicious agents
For years, prompt injection—the practice of embedding malicious commands into data to manipulate large language models (LLMs)—has been the primary weapon for cybercriminals looking to hijack autonomous AI agents. By slipping a well-crafted instruction into a seemingly benign calendar invite or email, attackers could coerce an LLM into exfiltrating sensitive corporate data or executing unauthorized […]
Tunisian Judiciary Imposes Harsh Prison Sentences on Human Rights Defenders Amid Deepening Crackdown on Civil Society
In a series of judicial rulings that have sent shockwaves through the international human rights community, Tunisian courts have sentenced several prominent activists to lengthy prison terms and astronomical fines, marking a significant escalation in the government’s efforts to dismantle the country’s once-vibrant civic space. On June 26, 2026, the Tunis Court of First Instance […]
