Cyber security

LLM Lies : Hallucinations Are Not Bugs, But Features As Adversarial Examples

LLMs (e.g., GPT-3.5, LLaMA, and PaLM) suffer from hallucination—fabricating non-existent facts to cheat users without perception. And the reasons for their existence and pervasiveness remain unclear.

We demonstrate that non-sense Out-of-Distribution(OoD) prompts composed of random tokens can also elicit the LLMs to respond with hallucinations.

This phenomenon forces us to revisit that hallucination may be another view of adversarial examples, and it shares similar features with conventional adversarial examples as the basic feature of LLMs.

Therefore, we formalize an automatic hallucination triggering method called hallucination attack in an adversarial way. Following is a fake news example generating by hallucination attack.

The Pipeline Of Hallucination Attack

We substitute tokens via gradient-based token replacing strategy, replacing token reaching smaller negative log-likelihood loss, and induce LLM within hallucinations.

Quick Start

Setup

You may config your own base models and their hyper-parameters within config.py. Then, you could attack the models or run our demo cases.

Demo

Clone this repo and run the code.

$ cd Hallucination-Attack

Install the requirements.

$ pip install -r requirements.txt

click here for more information.

Varshini

Varshini is a Cyber Security expert in Threat Analysis, Vulnerability Assessment, and Research. Passionate about staying ahead of emerging Threats and Technologies.

Recent Posts

SpyAI : Intelligent Malware With Advanced Capabilities

SpyAI is a sophisticated form of malware that leverages advanced technologies to capture and analyze…

3 days ago

Proxmark3 : The Ultimate Tool For RFID Security And Analysis

The Proxmark3 is a versatile, open-source tool designed for radio-frequency identification (RFID) security analysis, research,…

3 days ago

Awesome Solana Security : Enhancing Program Development

The "Awesome Solana Security" collection is a comprehensive resource designed to help developers build more…

3 days ago

IngressNightmare-POCs : Understanding The Vulnerability Exploitation Flow

The "IngressNightmare" vulnerabilities, disclosed in March 2025, represent a critical set of security issues affecting…

3 days ago

AdaptixC2 : Enhancing Penetration Testing With Advanced Framework Capabilities

AdaptixC2 is an advanced post-exploitation and adversarial emulation framework designed specifically for penetration testers. It…

3 days ago

Bincrypter : Enhancing Linux Binary Security through Runtime Encryption And Obfuscation

Bincrypter is a powerful Linux binary runtime crypter written in BASH. It is designed to…

3 days ago