Architecture Components

Fine-tuning Vulnerabilities

Vulnerabilities in model fine-tuning processes

13 matching entries out of 123 in this category

Fine-tuning research results

13 entries

Evolutionary Hidden Knowledge Recovery

Updated 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

Source: arXiv

LLM Backdoor Trigger Reconstruction

Updated 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

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

Source: arXiv

LLM Edit Fingerprint Leak

Updated 2/21/2026

A side-channel information leakage vulnerability exists in the "locate-then-edit" paradigm of Large Language Model (LLM) knowledge editing, specifically affecting algorithms such as ROME, MEMIT, and AlphaEdit. The parameter update matrix ($\Delta W$) generated during the editing process preserves the algebraic structure of the edited data. Specifically, the row space of the parameter difference matrix encodes a mathematical fingerprint of the key vectors associated with the edited subjects. An…

Reverse-Engineering Model Editing on Language Models

Affects: Llama 3 8B, Qwen 2.5 7B

Source: arXiv

Aggressive Compression Model Theft

Updated 2/21/2026

Large Language Models (LLMs) hosted on inference servers are vulnerable to high-speed weight exfiltration attacks due to the inherent compressibility of transformer parameters when decompression constraints are relaxed. Adversaries with compromised server access can utilize aggressive lossy compression techniques—specifically additive quantization combined with k-means clustering—to reduce model size by factors of 16x to 100x (e.g., <1 bit per parameter). Unlike standard quantization for…

Aggressive Compression Enables LLM Weight Theft

Affects: Qwen 2 1.5B, Qwen 2 7B, Qwen 2.5 0.5B +2 more

Source: arXiv

CoT Trajectory Data Leak

Updated 2/22/2026

Large Reasoning Models (LRMs) employing Chain-of-Thought (CoT) generation are vulnerable to sensitive information leakage through intermediate reasoning steps, even after undergoing standard unlearning procedures (such as Gradient Ascent, Direct Preference Optimization, or KL Minimization). While these fine-tuning-based unlearning methods typically suppress sensitive content in the final generated answer, they fail to purge the information from the model's internal reasoning trajectory…

STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models

Affects: o1, DeepSeek R1

Source: arXiv

LLM Input PII Leakage

Updated 2/22/2026

Unintended input-only PII memorization in fine-tuned Large Language Models (LLMs) allows remote attackers to extract sensitive Personally Identifiable Information (PII) such as names, medical records, and financial details. This vulnerability occurs when a model is fine-tuned on datasets where sensitive information appears in the input text, even if that information is not part of the training target (label) or is unrelated to the downstream task (e.g., classification). The fine-tuning process…

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models

Affects: Llama 3.1 8B, Llama 3.2 1B

Source: arXiv

Leaked Bits Collapse Attack Queries

Updated 12/9/2025

Large Language Models (LLMs), specifically variants of GPT-4o, DeepSeek-R1, OLMo-2, and Llama-4, are vulnerable to accelerated adaptive adversarial attacks due to excessive information leakage in observable output signals. When these models expose "thinking processes" (Chain-of-Thought traces) or token-level log-probabilities (logits) to the end user, they leak significant mutual information $I(Z;T)$ regarding the model's safety state or hidden instructions. This leakage allows adaptive attack…

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs

Affects: DeepSeek R1, GPT-4o Mini 2024-07-18, Llama 4 Maverick 17B +4 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

Enterprise Multi-Turn Data Exfiltration

Updated 7/28/2025

Large Language Model (LLM) systems integrated with private enterprise data, such as those using Retrieval-Augmented Generation (RAG), are vulnerable to multi-stage prompt inference attacks. An attacker can use a sequence of individually benign-looking queries to incrementally extract confidential information from the LLM's context. Each query appears innocuous in isolation, bypassing safety filters designed to block single malicious prompts. By chaining these queries, the attacker can…

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

Affects: GPT-2, GPT-3, GPT-4 +1 more

Source: arXiv

Cyber Fine-Tuning Undermines Safety

Updated 1/14/2026

Fine-tuning Large Language Models (LLMs) on the CyberLLMInstruct dataset results in a critical degradation of safety alignment and refusal mechanisms. While the dataset comprises "pseudo-malicious" content (educational descriptions of malware, phishing, and exploits without executable payloads), the Supervised Fine-Tuning (SFT) process on this corpus causes the models to generalize this instruction-following behavior to actual malicious requests. This effectively bypasses safety guardrails…

CyberLLMInstruct: A new dataset for analysing safety of fine-tuned LLMs using cyber security data

Affects: Llama 2 70B, Llama 3 8B, Llama 3.1 8B +4 more

Source: arXiv

Related research categories