This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

The paper introduces a hybrid system, HYBRIDSOURCETRACKER (HST), that combines vector search and Winnowing fingerprinting to achieve scalable, high-precision provenance tracking for code generated by…

The paper proposes SAFESEAL, a novel key-conditioned watermarking framework that embeds robust, provider-specific watermarks into LLM outputs with minimal semantic distortion, effectively protecting i…

This paper introduces Back-Reveal, an attack demonstrating that backdoored LLM agents can systematically exfiltrate sensitive user data by embedding semantic triggers into tool-use mechanisms.

The paper benchmarks local, offline LLMs for confidential translation workflows, demonstrating that while they are viable for privacy-sensitive use, they generally lag behind top commercial NMT system…

This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against…

This paper proposes four guidelines and two novel data ordering methods (STR and SAW) to systematically optimize data organization, significantly enhancing the stability and performance of LLM trainin…

The paper proposes SteganoPrompt, an input-side watermark embedded in the assignment prompt that forces LLMs to generate a detectable signature in their output, thereby exposing verbatim copy-pasting.

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

The paper introduces SIGIL, a novel framework that cryptographically seals the entire lifecycle of LLM skills, ensuring verifiable integrity from publication through runtime execution to prevent suppl…

This paper benchmarks LLMs for smart contract security analysis, concluding that while LLMs show potential, their reliability is limited by lexical bias and requires integration with traditional stati…

The paper demonstrates that using raw source text for fine-tuning LLMs on vulnerability detection causes high false-positive rates by memorizing surface-level syntax, a problem mitigated by using Abst…

The paper introduces a Retrieval-Augmented Generation (RAG) system that uses targeted query filtering and LLM semantic reasoning to accurately and cost-effectively analyze complex cybersecurity incide…

This paper proposes a structured pipeline using LLMs to generate and evaluate obfuscated XSS payloads, demonstrating that while LLMs can generate samples, they currently struggle to ensure payloads ma…

AsmRAG is a novel framework that improves malware detection by treating it as an evidence-based retrieval task using a code-specialized LLM, achieving high accuracy while providing transparent forensi…

The paper introduces FLIPS, an instance-level fingerprinting technique that exploits biases in generated random sequences to accurately distinguish between different configurations of the same Large L…

SilentRetrieval introduces a sophisticated, two-stage data poisoning attack that successfully hijacks Retrieval-Augmented Generation (RAG) systems by injecting adversarially crafted, yet highly fluent…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…