Adversarial Attacks

Neural Uncertainty Principle Links Adversarial Attacks to LLM Hal

A new theoretical framework unifies adversarial vulnerability in neural networks with LLM hallucination, proposing that both arise from a fundamental uncertainty trade-off in learned representations.

AI security

Adversarial AI Explanations: How Attackers Exploit Trust

New research reveals how adversarial attacks can manipulate AI explanation systems to mislead human decision-makers, with critical implications for content authenticity verification.

LLM Security

How Adversarial Attacks Circumvent LLM Safety Systems

Researchers detail how prompt injection, jailbreaking, and gradient-based attacks systematically defeat the layered safety mechanisms designed to keep large language models aligned and secure.

AI security

Visual Prompt Injection: How Hidden Images Hack AI Systems

Researchers reveal how imperceptible visual perturbations embedded in images can hijack vision-language models, bypassing safety filters and manipulating AI outputs without human detection.

LLM Security

AdvJudge-Zero: Adversarial Tokens Can Flip LLM Evaluator Decision

New research reveals how adversarial control tokens can manipulate LLM-as-a-Judge systems into completely reversing their binary decisions, exposing critical vulnerabilities in AI evaluation pipelines.

AI security

Multi-Agent LLMs Team Up to Break AI Safety Guardrails

New research demonstrates how multiple LLMs working together can generate adaptive adversarial attacks that bypass AI safety filters. The technique uses collaborative reasoning to craft prompts that exploit model vulnerabilities more effectively than single-agent approaches.

AI Detection

PADBen Benchmark Tests AI Text Detectors Against Attacks

New research introduces PADBen, a comprehensive benchmark evaluating how AI text detectors perform against paraphrase attacks. The framework reveals critical vulnerabilities in current detection systems through adversarial testing.