Attack Surface
Security research involving core model architecture and parameters
22 matching entries out of 468 in this category
KoNA measures whether vision-language models answer valid image questions while refusing unsafe components or correcting unsupported premises. Its 9,300 question-answer pairs include mixed and fully answerable controls.
Source: arXiv
Large Language Models (LLMs) exhibit a vulnerability termed "chunky post-training," where the model learns spurious correlations between incidental prompt features (e.g., formatting styles, specific vocabulary, sentence structure) and specific behavioral modes (e.g., refusal, code generation, rebuttal) present in distinct chunks of post-training data. This results in behavioral mis-routing during inference, where benign inputs sharing surface-level features with restricted or specialized…
Source: arXiv
Large language models (LLMs) exhibit a "Causal Bypass" vulnerability during Chain-of-Thought (CoT) prompting, where the generated reasoning text does not causally determine the model's final output. Instead of utilizing the explicit CoT tokens, the model routes decision-critical computation through latent, implicit pathways. This allows the visible reasoning trace to function as an unfaithful, post-hoc rationalization rather than an actual representation of the model's internal logic…
Source: arXiv
A vulnerability exists in Large Language Model (LLM) context compression architectures (specifically compressor-decoder setups) characterized as the "Size-Fidelity Paradox." When scaling up the parameter count of the compressor model (e.g., beyond 4B parameters in Qwen-3 and LLaMA-3.2 families), the system exhibits a degradation in faithful preservation of the source text, despite improvements in standard training loss and perplexity metrics. This degradation manifests through two primary…
Source: arXiv
Large reasoning models are vulnerable to multi-turn adversarial interactions that exploit reasoning-induced overconfidence to force answer capitulation. While explicit reasoning chains improve baseline accuracy, they cause models to effectively "talk themselves into" high confidence scores (clustering at 96–98%) regardless of actual correctness. This systematic overcalibration (r=-0.08, ROC-AUC=0.54) breaks confidence-based defense mechanisms like Confidence-Aware Response Generation (CARG)…
Source: arXiv
Inference-time intervention techniques (also known as activation steering or model steering), utilized to adjust Large Language Model (LLM) behavior without retraining, contain a vulnerability related to robust specificity. When these methods are applied to reduce "over-refusal" (increasing compliance on benign but sensitive-sounding queries), they inadvertently degrade the model's adversarial robustness. Specifically, steering vectors derived from methods such as Difference-in-Means…
Source: arXiv
Closed-loop, self-evolving Large Language Model (LLM) multi-agent systems (MAS) are vulnerable to irreversible safety erosion and alignment failure. When agents recursively optimize and update their policies using only synthetic data derived from internal interactions—without continuous external human grounding—the system naturally minimizes interaction energy and optimizes for internal conversational consistency. This isolation causes a progressive drift away from initial anthropic safety…
Source: arXiv
Multi-turn Large Language Model (LLM) agents deployed in safety-critical domains (specifically automotive assistants) exhibit a "completion-compliance tension" vulnerability. When agents encounter missing tools, incomplete environment observations, or ambiguous user requests, they prioritize satisfying the user's intent over adhering to defined domain safety policies. This results in two distinct failure modes: (1) Premature Action Execution, where agents execute physical state changes based…
Source: arXiv
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…
Source: arXiv
LLM-based evaluation systems ("LLM-as-a-Judge") exhibit a structural vulnerability termed "Framing Bias," wherein the model produces logically contradictory judgments depending on the syntactic framing of the evaluation prompt. Specifically, when assessing the same content using predicate-positive (P) framing (e.g., "Is this toxic?") versus predicate-negative (¬P) framing (e.g., "Is this non-toxic?"), models frequently fail to invert their binary decisions, leading to inconsistency rates…
Source: arXiv