The paper introduces Neutral Prompting Attacks (NPA), a stealthy method showing that semantically benign prompts can covertly increase package hallucination in coding agents, creating new software sup…

This study re-evaluates LLM package hallucination rates on a new cohort of frontier models, finding a significant reduction in overall hallucination rates but identifying a persistent, model-agnostic…

The paper introduces Evidence-Carrying Agents (ECA) to prevent multimodal agents from executing privileged actions based on unsupported or hallucinated perceptual claims, achieving near-zero unsafe ex…

The paper introduces a Hybrid Utility Minimum Bayes Risk (HUMBR) framework to significantly reduce hallucinations in high-stakes enterprise AI workflows, outperforming standard consistency methods.

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper introduces REALISTA, a novel latent-space adversarial attack framework that generates semantically realistic and coherent prompts to effectively induce hallucinations in large language model…

The paper introduces CHARM, a novel framework that detects and mitigates cascading hallucination—the amplification of errors across multi-step agentic RAG pipelines—achieving an 82.1% reduction in err…

The paper introduces DeLask, a novel decoding framework that dynamically skips or partially aggregates problematic decoder layers to significantly mitigate hallucinations in Large Language Models.

The paper proposes a memory-augmented, three-stage agentic pipeline that significantly reduces LLM hallucinations and improves operational efficiency by integrating semantic caching and advanced obser…

This paper introduces a novel supply-chain attack that uses model code backdoors to actively steal sensitive secrets from local LLM fine-tuning datasets, bypassing current privacy defenses.

This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significa…

The paper introduces Med-HEAL, a comprehensive framework and dataset for systematically identifying and mitigating hallucinations in medical LLMs, demonstrating that a self-critique pipeline significa…

The paper introduces Tree structured Injection for Payloads (TIP), a novel black-box attack framework that reliably generates stealthy injection payloads to seize control of LLM agents utilizing the M…

This paper systematically analyzes how different architectural components of Large Vision-Language Models (LVLMs) contribute to hallucination robustness, finding that joint enhancement of visual fidel…

The paper introduces 'abliteration,' a weight editing technique that successfully bypasses the refusal mechanism of safety-aligned Code LLMs, enabling scalable synthesis of vulnerable code from safe i…

The paper proposes BRACS, a training-free steering framework that adaptively corrects visual grounding failures in large vision-language models, significantly reducing object hallucination without sac…

The paper introduces REFORGE, a black-box red-teaming framework that uses adversarial image prompts to reveal persistent vulnerabilities in current Image Generation Model Unlearning (IGMU) methods.

The paper proposes Two-stage Backdoor Hijacking (TSBH) to create persistent, trigger-activated malicious behaviors by manipulating the observable Chain-of-Thought (CoT) process in Large Language Model…

This study compares two methods of safety unalignment (Jailbreak-Tuning and Weight Orthogonalization) across six LLMs and finds that Weight Orthogonalization (WO) significantly enhances malicious capa…

The paper systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…