Architecture Components

Fine-tuning Vulnerabilities

Vulnerabilities in model fine-tuning processes

4 matching entries out of 123 in this category

Fine-tuning research results

4 entries

Learned Reward Model Hacking

Updated 2/22/2026

Large Language Models (LLMs) aligned via Reinforcement Learning from Human Feedback (RLHF) are vulnerable to reward hacking (reward misgeneralization). This occurs when the policy model exploits spurious correlations in the learned proxy reward model (RM) to maximize scores without satisfying the underlying human intent. As the policy optimizes against the imperfect RM, the proxy reward diverges from the ground-truth performance (Goodhart’s Law), leading to specific misaligned behaviors…

Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking

Affects: GPT-4, Llama 2 7B

Source: arXiv

Detector Telemetry Camouflage

Updated 2/21/2026

Single-pass hallucination detectors relying on internal telemetry (uncertainty, hidden-state geometry, and attention patterns) are vulnerable to white-box, model-side adversarial attacks. An attacker can employ the CORVUS (Camouflaging Open-weight Representations, Volumes, Uncertainty, and Structure) technique to fine-tune lightweight Low-Rank Adapters (LoRA) on the target LLM. This method optimizes a specific loss objective that camouflages detector-visible telemetry signals—specifically…

CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models

Affects: Llama 2 7B, Llama 3 8B, Qwen 2.5 14B +1 more

Source: arXiv

RL Adversarial Function Call

Updated 2/22/2026

Large Language Models (LLMs) enabled with Function Calling (FC) capabilities are vulnerable to adversarial query rewriting and semantic manipulation. Standard FC models, typically trained via Supervised Fine-Tuning (SFT) on static datasets, fail to generalize against adversarial inputs that deviate from fixed distribution patterns. An attacker can exploit this by crafting queries that are semantically similar to valid requests but engineered to induce "bad cases," such as incorrect tool…

Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach

Affects: Qwen 2.5 7B Instruct, Qwen 3 0.6B, Qwen 3 4B +1 more

Source: arXiv

Prompt Injection Alignment Bypass

Updated 12/8/2025

Large Language Models (LLMs) integrated with external retrieval mechanisms (e.g., Retrieval-Augmented Generation (RAG), web search, or email processing) are vulnerable to Indirect Prompt Injection. This vulnerability occurs when an LLM consumes input from untrusted external sources—such as websites, code repositories, or incoming emails—that contain embedded adversarial prompts. Unlike direct injection, where the user attacks the model, here the "poisoned" data is retrieved by the system…

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs

Source: arXiv

Related research categories