Impact

Integrity Research

Security research involving model-output integrity and reliability

37 matching entries out of 539 in this category

Integrity research results

37 entries

Single-interaction poisoning of agent memory

Published Aug 24, 2026Analyzed Sep 9, 2026Source: arXiv

A stored interaction can later steer a memory-augmented agent's answer without direct memory-store access. The study evaluates persistent response manipulation in MemoryOS and MemGPT.

InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

Evaluated models: Qwen 2.5 7B Instruct, Qwen 2.5 1.5B Instruct, Qwen 2.5 3B Instruct+3 more

Qwen 2.5 7B Instruct
Qwen 2.5 1.5B Instruct
Qwen 2.5 3B Instruct
Qwen 2.5 14B Instruct
Llama 3.1 8B Instruct
Mistral 7B Instruct v0.3

Automated indirect prompt injection against tool-calling agents

Published Jun 9, 2026Analyzed Jul 21, 2026Source: arXiv

The paper presents a concrete, reproducible security evaluation in which attacker-controlled instructions embedded in retrieved external content steer stateful, tool-calling LLM agents toward unauthorized actions. It adapts white-box GCG and black-box TAP to AgentDojo and evaluates single-task and task-universal attacks across 80 task pairs in four domains. The reported results show that semantic black-box optimization can discover functional prompt injections more effectively than…

Assessing Automated Prompt Injection Attacks in Agentic Environments

Evaluated models: Gemma3-4B Instruct, Qwen 3 4B Instruct, GPT-5+6 more

Gemma3-4B Instruct
Qwen 3 4B Instruct
GPT-5
GPT-5 Mini
Qwen 3 32B
Qwen3-235B-A22B (MoE)
Qwen3-235B-A22B-Thinking (MoE)
Claude Sonnet 4.5
Gemini 2.5 Flash

Fluent Single-Document RAG Corpus Poisoning

Published May 27, 2026Analyzed Jul 20, 2026Source: arXiv

SilentRetrieval describes a specific RAG corpus-integrity vulnerability: an attacker able to add a topically relevant document to a retrieval corpus can make that document rank highly and influence the generated answer while remaining fluent enough to evade simple perplexity checks. The paper evaluates a two-stage method combining retrieval-oriented document optimization with context-adaptive claim integration. A safe defensive reproduction is to use only isolated benchmark corpora and inert…

SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning

Evaluated models: Llama 2 7B Chat, Mistral 7B Instruct v0.2, Qwen 7B Chat+1 more

Llama 2 7B Chat
Mistral 7B Instruct v0.2
Qwen 7B Chat
GPT-3.5 Turbo

LLM Judge Manipulation

Published Mar 31, 2026Analyzed Apr 10, 2026Source: arXiv

Generative reward models deployed as LLM-as-a-Judge (LaaJ) evaluators contain a logic bypass vulnerability where superficial "master key" inputs trigger false positive rewards regardless of actual response quality. Instead of evaluating the candidate's output, large judge models are inadvertently triggered by specific token sequences to solve the prompt independently. This allows malicious actors or policy models undergoing reinforcement learning to consistently game the reward signal by…

Security in LLM-as-a-Judge: A Comprehensive SoK

Evaluated models: GPT-4o, o1, Qwen 2.5 72B Instruct+1 more

GPT-4o
o1
Qwen 2.5 72B Instruct
Llama 3 70B Instruct

Autoresearch Adversarial Algorithm Discovery

Published Mar 25, 2026Analyzed Apr 11, 2026Source: arXiv

GPT-OSS-Safeguard-20B and Meta-SecAlign (70B/8B) are vulnerable to white-box adversarial attacks generated by automated algorithmic recombination (specifically the claude_v63, claude_v82, and claude_v53-oss optimizers). These algorithms significantly outperform standard discrete optimization methods (like GCG) by integrating continuous optimization (ADC) with LayerNorm gradient scaling (LSGM), or by merging momentum-smoothed gradients with directional perturbation candidate selection (DPTO)…

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Evaluated models: Llama 2 7B, Llama 3 8B, Qwen 2.5 7B+2 more

Llama 2 7B
Llama 3 8B
Qwen 2.5 7B
Gemma 2 2B
Gemma 7B

Visual Memory Multi-Turn Manipulation

Published Feb 17, 2026Analyzed Mar 8, 2026Source: arXiv

Large Vision-Language Models (LVLMs) are vulnerable to Visual Memory Injection (VMI), a stealthy targeted attack targeting multi-turn conversations. An attacker can embed an imperceptible adversarial perturbation ($L_\infty \le 8/255$) into a seemingly benign image. Because the visual input persists in the model's context throughout a multi-turn dialogue, the injected payload remains dormant. By utilizing "benign anchoring" and "context-cycling" during optimization, the attacker ensures the…

Visual Memory Injection Attacks for Multi-Turn Conversations

Evaluated models: Qwen 2.5 VL 7B Instruct, Qwen3-VL 8B Instruct, LLaVA-OneVision 1.5 8B Instruct+2 more

Qwen 2.5 VL 7B Instruct
Qwen3-VL 8B Instruct
LLaVA-OneVision 1.5 8B Instruct
Qwen-SEA-LION v4 8B VL
QoQ-Med3-VL 8B

Covert Grade Manipulation

Published Feb 1, 2026Analyzed Feb 22, 2026Source: arXiv

Large Language Models (LLMs) utilized for Automatic Short Answer Grading (ASAG) are vulnerable to the "GradingAttack" framework, which employs fine-grained adversarial manipulation to alter grading outcomes. Attackers can leverage two distinct strategies: (1) Prompt-level attacks using role-play injection strings that instruct the model to pretend an answer is correct regardless of factual accuracy, and (2) Token-level attacks utilizing gradient-based optimization (similar to Greedy Coordinate…

GradingAttack: Attacking Large Language Models Towards Short Answer Grading Ability

Evaluated models: GPT-3.5, GPT-4, GPT-4o+3 more

GPT-3.5
GPT-4
GPT-4o
Llama 3.1 8B
Mistral 7B
Qwen 2.5 7B

Activation Delta Detector Evasion

Published Jan 31, 2026Analyzed Mar 9, 2026Source: arXiv

Activation-delta-based linear probes used for detecting task drift and prompt injections in Large Language Models (LLMs) can be bypassed using universal adversarial suffixes. By utilizing the Greedy Coordinate Gradient (GCG) algorithm, an attacker can generate a single, optimized suffix that simultaneously fools multiple logistic regression classifiers attached to different hidden layers of the LLM. The attack jointly optimizes the suffix tokens by accumulating gradients from the losses of all…

Bypassing Prompt Injection Detectors through Evasive Injections

Evaluated models: Llama 3 8B, Phi-3 8B

Unified Robustness Gap

Published Jan 31, 2026Analyzed Mar 9, 2026Source: arXiv

Text scoring models, including dense retrievers, rerankers, and reward models, are vulnerable to score manipulation attacks via search-based discrete perturbations and content injection. An attacker can systematically modify candidate texts using rudimentary string manipulations, gradient-guided token swaps (e.g., HotFlip), masked language modeling (MLM) swaps, or query/sentence injections to spuriously increase model scores. This structural failure condition allows an irrelevant passage or a…

Unifying Adversarial Robustness and Training Across Text Scoring Models

Evaluated models: E5 BERT-base, Qwen 3 0.6B, Llama 3.2 3B Instruct+2 more

E5 BERT-base
Qwen 3 0.6B
Llama 3.2 3B Instruct
Llama 3.1 8B Instruct
Skywork Reward V2

LLM Router Rerouting

Published Jan 29, 2026Analyzed Mar 8, 2026Source: arXiv

LLM routing systems are vulnerable to adversarial rerouting attacks where malicious triggers prepended to user queries manipulate the router's model-selection mechanism. Because LLM routers function as classifiers evaluating query complexity to balance computational cost and response quality, an attacker can craft adversarial prefixes that distort the query's latent semantic representation. This exploits the router's decision boundaries, forcing the system to misclassify the input and redirect…

RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing

Evaluated models: GPT-4, GPT-4o, GPT-5+2 more

GPT-4
GPT-4o
GPT-5
Llama 3 8B
Mixtral 8x7B

Related research categories