This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

This paper provides a systematic, lifecycle-based framework for analyzing security threats and defenses across the entire fine-tuning process of LLMs, revealing that attack effectiveness is highly mod…

The paper introduces Semantic Compliance Hijacking (SCH), a novel payload-less attack that exploits LLM agent supply chains by manipulating compliance rules to force unauthorized code generation, achi…

The paper introduces Tree-like Self-Play (TSP), a novel framework that treats secure code generation as a fine-grained decision process, significantly improving LLM security by forcing the model to se…

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 a systematic benchmark to test LLMs' ability to recover Indicators of Compromise (IoCs) from JavaScript code, finding that while LLMs handle simple obfuscation well, encryption-ba…

This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.

RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, signi…

The paper introduces LeakDojo, a framework that systematically evaluates RAG leakage risks, finding that stronger LLM instruction-following and query generation are major independent contributors to d…

The paper introduces DiffusionHijack, a supply-chain backdoor attack that compromises the PRNG used by diffusion models to deterministically control generated images, which is successfully mitigated b…

The paper introduces Sparse Backdoor, a novel supply-chain attack that embeds a provably undetectable backdoor into pre-trained image classifiers by injecting structured sparse perturbations.

This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a signific…

The paper introduces Document-Driven Implicit Payload Execution (DDIPE) to demonstrate that malicious code can be embedded in LLM agent skill documentation, allowing supply-chain attacks to hijack age…

The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific…

This paper empirically demonstrates that current Static Application Security Testing (SAST) tools are fundamentally unreliable against common JavaScript obfuscation techniques, showing that obfuscatio…

This paper introduces Dependency Steering, a novel attack paradigm demonstrating that malicious agent skills can actively bias LLM coding agents to use attacker-controlled packages, posing a significa…

The paper introduces CIPL, a unified channel-oriented framework, demonstrating that privacy leakage in LLM agents is governed by observable data channels and pipeline interactions, rather than being l…

The paper analyzes LLM vulnerability detection using mechanistic interpretability, finding that models primarily rely on safety detectors rather than direct vulnerability signature recognition.

SecureForge is an automated pipeline that significantly reduces cybersecurity vulnerabilities in LLM-generated code by optimizing system prompts, achieving up to a 48% reduction in output vulnerabilit…

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…