Al Mayadeen English

  • Ar
  • Es
  • x
Al Mayadeen English

Slogan

  • News
    • Politics
    • Economy
    • Sports
    • Arts&Culture
    • Health
    • Miscellaneous
    • Technology
    • Environment
  • Articles
    • Opinion
    • Analysis
    • Blog
    • Features
  • Videos
    • NewsFeed
    • Video Features
    • Explainers
    • TV
    • Digital Series
  • Infographs
  • In Pictures
  • • LIVE
News
  • Politics
  • Economy
  • Sports
  • Arts&Culture
  • Health
  • Miscellaneous
  • Technology
  • Environment
Articles
  • Opinion
  • Analysis
  • Blog
  • Features
Videos
  • NewsFeed
  • Video Features
  • Explainers
  • TV
  • Digital Series
Infographs
In Pictures
  • Africa
  • Asia
  • Asia-Pacific
  • Europe
  • Latin America
  • MENA
  • Palestine
  • US & Canada
BREAKING
Palestinian media: Herds of Israeli settlers storm the al-Aqsa Mosque and perform Talmudic rituals in it
Al Mayadeen's correspondent in Gaza: 15 martyrs were transferred to hospitals in the Gaza Strip in the past few hours as the Israeli occupation continues its aggression on the camps of the displaced
Al Mayadeen's correspondent in Gaza: 38 were killed since dawn on Saturday, as the Israeli occupation army targeted aid seekers at distribution sites
Palestinian Red Crescent: One martyr, several injuries among our teams after the occupation bombed the association's headquarters in al-Amal neighborhood, west of Khan Younis.
Sirens sound in Gaza Envelope settlements.
Al Mayadeen's correspondent in Gaza: Infant dies of malnutrition, four martyrs killed by Israeli-made famine in past 24 hours.
Al Mayadeen's correspondent in Gaza: 12 martyrs and more than 90 wounded in Israeli shooting of aid seekers in central Gaza.
US President Donald Trump to Newsmax: Nuclear submarines are closer to Russia.
Hamas: Continuing negotiations amid starvation strips them of meaning and value
Hamas: We affirm our readiness to immediately re-engage in negotiations if aid reaches those in need and the humanitarian crisis and famine in Gaza are resolved

Most AI chatbots vulnerable to jailbreaks, study warns

  • By Al Mayadeen English
  • Source: News websites
  • 21 May 2025 14:45
  • 1 Shares
4 Min Read

A universal jailbreak tricked top AI chatbots into giving harmful answers, exposing major security flaws in LLM design and regulation.

Listen
  • x
  • The OpenAI logo appears on a mobile phone in front of a screen showing part of the company website in this photo taken on November 21, 2023 in New York (AP/Peter Morgan)
    The OpenAI logo appears on a mobile phone in front of a screen showing part of the company website in this photo taken on November 21, 2023 in New York (AP/Peter Morgan)

A new academic report has found that most popular AI-powered chatbots are easily tricked into producing harmful and illegal content. The study highlights what it describes as a “tangible and deeply concerning” threat, as “jailbroken” chatbots can now deliver illicit information they absorbed during training.

Despite built-in safety systems intended to block inappropriate or dangerous queries, researchers say these protections can be bypassed through jailbreaking, specially crafted prompts designed to override safety guardrails.

Chatbots such as ChatGPT, Gemini, and Claude rely on large language models (LLMs) trained on massive troves of internet data, which contain material related to illegal activities, including hacking, money laundering, drug manufacturing, and bomb-making. While efforts have been made to filter such content from training datasets, the underlying models still retain knowledge of it.

According to the researchers, jailbreaks exploit a fundamental tension in LLM design: while the primary objective of these models is to fulfill user commands, their safety measures are secondary, making them vulnerable to manipulation.

Researchers develop a universal jailbreak

The study was led by Professor Lior Rokach and Dr. Michael Fire of Ben Gurion University of the Negev in the occupied Palestinian territories. Their team developed a universal jailbreak that successfully compromised multiple leading AI chatbots, compelling them to respond to nearly any prompt, including those that would normally trigger a refusal.

“It was shocking to see what this system of knowledge consists of,” said Fire. The researchers documented instances in which chatbots, once jailbroken, provided detailed guidance on hacking, drug manufacturing, and other criminal activities.

Rokach emphasized the unprecedented danger posed by this capability. “What sets this threat apart from previous technological risks is its unprecedented combination of accessibility, scalability, and adaptability,” he said.

Some of the dark LLMs identified in the study are explicitly marketed online as having "no ethical guardrails" and promoting their willingness to assist in cybercrime, fraud, and other illegal activities.

AI companies fail to respond adequately

After identifying the vulnerability, the researchers alerted major LLM providers. However, they described the response as “underwhelming,” while several companies either failed to respond or dismissed the jailbreak issue as outside the scope of their security bounty programs, which are designed to reward ethical hackers for reporting vulnerabilities.

The authors argue that without a serious shift in how tech firms address model-level risks, AI security will remain fragile. They call for comprehensive screening of training data, the deployment of robust query firewalls, and the development of "machine unlearning" methods to help chatbots forget dangerous material.

According to the report, dark LLMs should be classified as severe security threats, comparable to unlicensed weapons or explosives, and providers should face accountability for any misuse.

Dark LLMs compared to unlicensed weapons

External experts have shared the same concerns raised by the study. Dr. Ihsen Alouani, a researcher in AI security at Queen’s University Belfast, warned that jailbreak attacks on LLMs could enable real-world harm, from disinformation and social engineering to automated scams and weapon-making guides.

“A key part of the solution is for companies to invest more seriously in red teaming and model-level robustness techniques, rather than relying solely on front-end safeguards,” Alouani said, adding, “We also need clearer standards and independent oversight to keep pace with the evolving threat landscape.”

Commented for @Forbes on the dangers of poorly trained #AI

The recent story of Google Gemini outputting harmful content to its users highlights the #risks of operating #LLMs and the critical need for continuous testing of models and their guardrails https://t.co/pxv0hYLyoW

— Peter Garraghan (@DrGarraghan) November 27, 2024

Professor Peter Garraghan of Lancaster University, who specializes in AI security, agreed that current safeguards are insufficient. “Organisations must treat LLMs like any other critical software component, one that requires rigorous security testing, continuous red teaming and contextual threat modelling,” he said.

Garraghan added that meaningful AI security demands not only responsible disclosure but also responsible design and deployment.

Industry responds to growing pressure

OpenAI, the company behind ChatGPT, responded by pointing to improvements in its latest “o1” model, which it says demonstrates increased resilience to jailbreak attempts due to its ability to reason about internal safety policies.

Microsoft, another major AI provider, shared a blog post outlining its ongoing work to strengthen protections against such exploits. Other tech giants, including Meta, Google, and Anthropic, have yet to publicly respond to the study’s findings.

  • Artificial Intelligence
  • ChatGPT
  • gemini
  • jailbroken AI
  • LLMs
  • Chatbots
  • AI security

Most Read

Given ample indications Epstein was collating sexual blackmail material on powerful figures for intelligence agencies, comments made by Mirage's cofounder to Ynet take on a chilling character. (Al Mayadeen English; Illustrated by Batoul Chamas)

Zionist spies innovate AI sexual blackmail tech

  • Analysis
  • 27 Jul 2025
A rescued crew member from the ETERNITY C vessel in a video released by the Yemeni Armed Forces on July 28, 2025 (Yemeni Military Media)

Yemen Navy reveals fate of targeted Eternity C ship crew

  • Politics
  • 28 Jul 2025
An Israeli tank explodes following an ambush by al-Qassam Brigades in Gaza, Occupied Palestine, undated (Al-Qassam Military Media)

Al-Qassam strikes Israeli vehicles in Gaza, inflicts casualties

  • Politics
  • 30 Jul 2025
UAE lodges complaint against Israeli ambassador over 'misbehavior'

UAE lodges complaint against Israeli ambassador over 'misbehavior'

  • Politics
  • 1 Aug 2025

Coverage

All
The Ummah's Martyrs

Read Next

All
A screengrab from a video shared by the al-Qassam Brigades Military Media wing showing the targeting of Israeli soldiers in Khan Younis, southern Gaza, August 2, 2025 (Al-Qassam Brigades Military Media)
Politics

Palestinian resistance targets Israeli forces in southern Khan Younis

Turkish President Recep Tayyip Erdogan gestures during a press conference after the plenary session at the NATO summit in The Hague, Netherlands, Wednesday, June 25, 2025 (AP)
Politics

Report questions Turkey’s role in future European defense plans

Pentagon faces turmoil under Hegseth’s strained leadership
US & Canada

Pentagon faces turmoil under Hegseth’s strained leadership

Ex Shin Bet official: Hamas will never surrender, even after 100 years
Palestine

Ex Shin Bet official: Hamas will never surrender, even after 100 years

Al Mayadeen English

Al Mayadeen is an Arab Independent Media Satellite Channel.

All Rights Reserved

  • x
  • Privacy Policy
  • About Us
  • Contact Us
  • Authors
Android
iOS