The paper introduces TrojanMerge, a framework demonstrating that model merging can be exploited to systematically compromise the safety alignment of multiple individually safe LLMs.

This paper demonstrates that LLM cascade systems, designed for efficiency, are vulnerable to targeted adversarial attacks that simultaneously degrade both performance and cost-efficiency.

The paper proposes a general-purpose pipeline to train automated red teaming models capable of generating attacks for arbitrary adversarial goals, overcoming the limitations of current methods that ar…

DarkLLM introduces a novel framework that uses a Large Language Model (LLM) to translate natural language instructions into flexible, latent adversarial attack vectors, demonstrating a systemic vulner…

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

The paper introduces LAAF, a novel automated red-teaming framework, to systematically test and exploit Logic-layer Prompt Control Injection (LPCI) vulnerabilities in complex agentic LLM systems.

The paper introduces a quality-diversity evolutionary framework that evolves interpretable attack strategies, successfully discovering distinct and systematic vulnerabilities in major LLMs like GPT-4o…

The paper introduces a quality-diversity evolutionary framework that discovers diverse, interpretable vulnerabilities in large language models by evolving attack strategies at the semantic level, reve…

The paper establishes a standardized security assessment framework and develops a multi-layered defensive system, demonstrating that systematic testing and external defenses are crucial for safe LLM d…

The paper introduces SHADOWMERGE, a novel poisoning attack that successfully compromises graph-based agent memory by exploiting relation-channel conflicts, achieving a high attack success rate across…

CoopGuard is a novel stateful, multi-round defense framework using cooperative agents to significantly reduce the success rate of evolving adversarial attacks against Large Language Models.

This review analyzes the dual impact of integrating Large Language Models (LLMs) into hardware design, detailing both their transformative potential in EDA and the critical security vulnerabilities th…

The paper introduces a comprehensive taxonomy and auditing framework to assess the collective coverage of existing LLM attack benchmarks, revealing significant and systematic gaps in current testing m…

This paper quantifies the polymorphic capacity of a commercial LLM, demonstrating that it can cheaply generate large populations of structurally diverse, yet behaviorally equivalent, offensive code pa…

The paper evaluates the adversarial robustness of two open-source Vision-Language Models (LLaVA and Qwen2.5-VL) in a simulated e-commerce environment, finding that while LLaVA is vulnerable to gradien…

This study longitudinally evaluates the adversarial robustness of Android malware detection systems over a decade, finding that temporal separation significantly degrades robustness due to concept dri…

The paper identifies a critical vulnerability, the Camouflage Detection Gap (CDG), where standard LLM injection detectors fail dramatically when malicious payloads mimic the target domain's language a…

This paper introduces the Token by Token Backdoor Attack (ToBAC), demonstrating that unified autoregressive models (UAMs) are vulnerable to backdoor attacks where a single trigger can compromise multi…

The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across divers…

This paper introduces a novel supply-chain attack that uses model code backdoors to actively steal sensitive secrets from local LLM fine-tuning datasets, bypassing current privacy defenses.