Menu

  • Alerts
  • Incidents
  • News
  • APTs
  • Cyber Decoded
  • Cyber Hygiene
  • Cyber Review
  • Cyber Tips
  • Definitions
  • Malware
  • Threat Actors
  • Tutorials

Useful Tools

  • Password generator
  • Report an incident
  • Report to authorities
No Result
View All Result
CTF Hack Havoc
CyberMaterial
  • Education
    • Cyber Decoded
    • Definitions
  • Information
    • Alerts
    • Incidents
    • News
  • Insights
    • Cyber Hygiene
    • Cyber Review
    • Tips
    • Tutorials
  • Support
    • Contact Us
    • Report an incident
  • About
    • About Us
    • Advertise with us
Get Help
Hall of Hacks
  • Education
    • Cyber Decoded
    • Definitions
  • Information
    • Alerts
    • Incidents
    • News
  • Insights
    • Cyber Hygiene
    • Cyber Review
    • Tips
    • Tutorials
  • Support
    • Contact Us
    • Report an incident
  • About
    • About Us
    • Advertise with us
Get Help
No Result
View All Result
Hall of Hacks
CyberMaterial
No Result
View All Result
Home Alerts

Bad Likert Judge Bypasses AI Safety Measures

January 3, 2025
Reading Time: 2 mins read
in Alerts
Bad Likert Judge Bypasses AI Safety Measures

Researchers at Palo Alto Networks’ Unit 42 have discovered a new AI jailbreak technique known as “Bad Likert Judge,” which manipulates large language models (LLMs) to bypass safety measures. The attack targets the model’s ability to judge and score the harmfulness of given prompts, exploiting the common Likert scale system used in surveys. By asking the LLMs to evaluate the harmfulness of specific content and provide examples for different scores, attackers can manipulate the system into generating harmful responses. This breakthrough method has demonstrated a significant success rate, with the technique increasing the attack’s effectiveness by over 60%.

The attack works by prompting the LLMs indirectly, first by asking them to assess the harmfulness of various content based on a predefined scale. Once the model provides its initial judgments, follow-up prompts encourage the chatbot to refine its responses, often leading to more harmful content. This sequence has been shown to significantly outpace direct attacks, with researchers reporting over 75 percentage points higher success rates compared to standard attack methods. In some cases, the attack success rate exceeded 80%, making it a highly effective approach for bypassing AI safety features.

Unit 42’s testing of six state-of-the-art LLMs revealed that some models, particularly those addressing sensitive topics like harassment, exhibited weaker protections. This vulnerability highlights the challenges AI developers face in safeguarding against sophisticated manipulation techniques. The researchers also observed that content moderation filters, when implemented, could reduce the attack’s success rate by up to 89.2%. However, the effectiveness of these filters is not foolproof, and there is still a risk of adversaries finding new ways to circumvent protections.

While content filtering plays a crucial role in defending against this type of attack, it is not a complete solution. False positives and negatives introduced by filtering processes could impact the accuracy of moderation systems. As AI technologies continue to evolve, this research underscores the importance of continuously enhancing security measures and content moderation systems to protect users from malicious actors. The findings from Unit 42 serve as a reminder of the persistent challenges AI safety faces, especially as large-scale models become more prevalent in real-world applications.

Reference:

  • Bad Likert Judge Attack Bypasses AI Safety Measures with 60% Success Rate
Tags: AIBad Likert JudgeCyber AlertsCyber Alerts 2025CybersecurityjailbreakJanuary 2025
ADVERTISEMENT

Related Posts

Hackers Target Libraesva Email Flaw

Hackers Target Libraesva Email Flaw

September 30, 2025
Hackers Target Libraesva Email Flaw

ShadowV2 Botnet Targets Misconfigured AWS

September 30, 2025
Hackers Target Libraesva Email Flaw

Cisco Warns Of IOS Zero Day Bug

September 30, 2025
Fake Microsoft Teams Installers Spread

Fake Microsoft Teams Installers Spread

September 30, 2025
Fake Microsoft Teams Installers Spread

Cybercriminals Use Facebook Google Ads

September 30, 2025
Fake Microsoft Teams Installers Spread

CISA Warns Of Critical Sudo Flaw

September 30, 2025

Latest Alerts

Hackers Target Libraesva Email Flaw

ShadowV2 Botnet Targets Misconfigured AWS

Cisco Warns Of IOS Zero Day Bug

CISA Warns Of Critical Sudo Flaw

Cybercriminals Use Facebook Google Ads

Fake Microsoft Teams Installers Spread

Subscribe to our newsletter

    Latest Incidents

    Ukrainian Hackers Breach Crimean Servers

    Ransomware Gang Claims Maryland Breach

    Arizona School District Data Breach

    Attackers Take Down Asahi Brewer

    Harrods Alerts Customers To Breach

    Hackers Steal Photos From Kido Nursery

    CyberMaterial Logo
    • About Us
    • Contact Us
    • Jobs
    • Legal and Privacy Policy
    • Site Map

    © 2025 | CyberMaterial | All rights reserved

    Welcome Back!

    Login to your account below

    Forgotten Password?

    Retrieve your password

    Please enter your username or email address to reset your password.

    Log In

    Add New Playlist

    No Result
    View All Result
    • Alerts
    • Incidents
    • News
    • Cyber Decoded
    • Cyber Hygiene
    • Cyber Review
    • Definitions
    • Malware
    • Cyber Tips
    • Tutorials
    • Advanced Persistent Threats
    • Threat Actors
    • Report an incident
    • Password Generator
    • About Us
    • Contact Us
    • Advertise with us

    Copyright © 2025 CyberMaterial