Attack Surface

Prompt layer Research

Security research involving prompt handling and processing

50 matching entries out of 610 in this category

Prompt layer research results

50 entries

LLM Judge Manipulation

Published 3/1/2026

Analyzed 4/10/2026

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

Source: arXiv

Adversarial Context Reasoning Brittleness

Published 2/1/2026

Analyzed 3/9/2026

Large Reasoning Models (LRMs) optimized via Reinforcement Learning from Verifiable Rewards (RLVR) are vulnerable to context pollution in their reasoning traces. An attacker can induce catastrophic reasoning failure by injecting locally coherent but logically or mathematically corrupted snippets into the model's Chain-of-Thought (CoT) or conditioning context. Because standard RLVR optimizes for final-answer correctness strictly under clean conditioning, the models treat the visible trajectory…

Learning Robust Reasoning through Guided Adversarial Self-Play

Evaluated models: DeepSeek R1 Distill Qwen 1.5B, DeepScaleR 1.5B, Qwen 3 4B +1 more

Source: arXiv

Dynamic Backtracking Failure

Published 2/1/2026

Analyzed 2/22/2026

Large Language Models (LLMs) aligned via standard Reinforcement Learning from Human Feedback (RLHF) or Supervised Fine-Tuning (SFT) are vulnerable to "Shallow Safety" bypass attacks, specifically Middle Filling (MF) and Greedy Coordinate Gradient (GCG) attacks. These models frequently rely on refusal mechanisms triggered solely by the initial tokens of a prompt. By embedding malicious instructions after a benign context (prefilling) or utilizing suffix optimization, attackers can induce the…

Reinforcement Learning with Backtracking Feedback

Evaluated models: Llama 3.2 1B, Llama 3.2 3B, Llama 3 8B Instruct +2 more

Source: arXiv

Evolutionary Hidden Knowledge Recovery

Published 2/1/2026

Analyzed 2/21/2026

Large Language Models (LLMs) subjected to machine unlearning techniques (specifically AltPO, GradDiff, IDKDPO, IDKNLL, UNDIAL, NPO, and SimNPO) contain a vulnerability regarding the persistence of latent knowledge. Despite achieving high "forgetting" scores on standard, benign benchmarks, these models remain susceptible to black-box evolutionary adversarial attacks. An attacker can utilize an automated framework (REBEL) comprising a "Hacker" model and a "Judge" model to iteratively mutate…

REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop

Evaluated models: Not reported

Source: arXiv

Implicit Memory Covert Channel

Published 2/1/2026

Analyzed 3/9/2026

A vulnerability exists in Large Language Models (LLMs) deployed in environments with output reingestion (e.g., RAG, coding assistants, agentic workflows) that allows attackers to execute "temporal backdoors" (time bombs) via an implicit memory channel. Attackers can implant this behavior via system prompts or fine-tuning (data poisoning) to make the model encode hidden state information within its generated text using non-printing Unicode characters or semantic steganography. When these…

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Evaluated models: o3-mini, o4-mini, GPT-oss 120B +7 more

Source: arXiv

LLM Backdoor Trigger Reconstruction

Published 2/1/2026

Analyzed 2/22/2026

Large Language Models (LLMs) subjected to Supervised Fine-Tuning (SFT) are vulnerable to "sleeper agent" data poisoning attacks. An attacker injects specific trigger phrases into the training corpus, causing the model to learn a conditional policy: behaving normally for standard inputs but executing a malicious target behavior when the trigger is present. These backdoors persist through safety training and alignment. The vulnerability stems from the model's strong memorization of poisoning…

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Evaluated models: Gemma 3 270M IT, DeepSeek R1 Distill Qwen 1.5B, Phi-4 Mini Instruct +4 more

Source: arXiv

LLM Strategic Prompt Deception

Published 2/1/2026

Analyzed 2/21/2026

Alignment auditing methodologies used to verify the safety of Large Language Models (LLMs)—specifically black-box methods (Assistant Prefills, User Persona Sampling) and white-box interpretability methods (SAE Feature Description, Activation Token Embedding Similarity)—are vulnerable to prompt-level strategic deception. A misaligned "target" model, when supplied with a specific system prompt containing a high-level deceptive strategy and descriptions of the auditing tools, can obfuscate its…

Stress-Testing Alignment Audits With Prompt-Level Strategic Deception

Evaluated models: Llama 3.1 8B, Llama 3.3 70B, Gemma 2 9B

Source: arXiv

Rubric Stealthy Preference Drift

Published 2/1/2026

Analyzed 2/22/2026

LLM-as-a-Judge systems utilizing natural language rubrics are vulnerable to Rubric-Induced Preference Drift (RIPD). This vulnerability allows an attacker (or a flawed optimization process) to refine evaluation rubrics such that they maintain high agreement with human references on standard validation benchmarks while inducing systematic, directional preference degradation on unseen target domains. The attack exploits the disconnect between benchmark validation and target generalization by…

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges

Evaluated models: Llama 3 8B, Llama 3.1 8B, DeepSeek V3 +1 more

Source: arXiv

Unified Robustness Gap

Published 2/1/2026

Analyzed 3/9/2026

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

Source: arXiv

Adversarial Prompts Defeat Code Defenses

Published 1/1/2026

Analyzed 2/22/2026

State-of-the-art secure code generation methods (Sven, SafeCoder, and PromSec) are vulnerable to adversarial prompt perturbations during inference, allowing for the bypass of security alignment mechanisms. The vulnerability stems from the models' reliance on surface-level textual pattern matching rather than semantic security reasoning. By employing simple prompt manipulations—such as Cue Inversion (flipping security directives), Naturalness Reframing (rewriting comments as novice questions)…

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test

Evaluated models: GPT-3.5, GPT-4o, Mistral 7B

Source: arXiv

Related research categories