While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components governing safety. Existing methods rely on local, greedy attribution that assumes independent component contributions. However, they overlook the cooperative interactions between different components in LLMs, such as attention heads, which jointly contribute to safety mechanisms. We propose Global Optimization for Safety Vector Extraction (GOSV), a framework that identifies safety-critical attention heads through global optimization over all heads simultaneously. We employ two complementary activation repatching strategies: Harmful Patching and Zero Ablation. These strategies identify two spatially distinct sets of safety vectors with consistently low overlap, termed Malicious Injection Vectors and Safety Suppression Vectors, demonstrating that aligned LLMs maintain separate functional pathways for safety purposes. Through systematic analyses, we find that complete safety breakdown occurs when approximately 30% of total heads are repatched across all models. Building on these insights, we develop a novel inference-time white-box jailbreak attack and a complementary detection-based defense, both grounded in the identified safety vectors. The attack achieves superior performance, while the defense yields strong detection across diverse attack types, providing robust evidence for the effectiveness of the proposed GOSV framework in LLM safety interpretability.

The increasing misuse of AI-generated texts (AIGT) has motivated the rapid development of AIGT detection methods. However, the reliability of these detectors remains fragile against adversarial evasions. Existing attack strategies often rely on white-box assumptions or demand prohibitively high computational and interaction costs, rendering them ineffective under practical black-box scenarios. In this paper, we propose Multi-stage Alignment for Style Humanization (MASH), a novel framework that evades black-box detectors based on style transfer. MASH sequentially employs style-injection supervised fine-tuning, direct preference optimization, and inference-time refinement to shape the distributions of AI-generated texts to resemble those of human-written texts. Experiments across 6 datasets and 5 detectors demonstrate the superior performance of MASH over 11 baseline evaders. Specifically, MASH achieves an average Attack Success Rate (ASR) of 92%, surpassing the strongest baselines by an average of 24%, while maintaining superior linguistic quality.

Introducing reasoning models into Retrieval-Augmented Generation (RAG) systems enhances task performance through step-by-step reasoning, logical consistency, and multi-step self-verification. However, recent studies have shown that reasoning models suffer from overthinking attacks, where models are tricked to generate an unnecessarily high number of reasoning tokens. In this paper, we reveal that such overthinking risk can be inherited by RAG systems equipped with reasoning models, by proposing an end-to-end attack framework named Contradiction-Based Deliberation Extension (CODE). Specifically, CODE develops a multi-agent architecture to construct poisoning samples that are injected into the knowledge base. These samples 1) are highly correlated with the user query, such that they can be retrieved as inputs to the reasoning model; and 2) contain contradiction between the logical and evidential layers that cause models to overthink, and are optimized to exhibit highly diverse styles. Extensive experiments on two datasets across five commercial reasoning models demonstrate that the proposed attack causes a 5.32∼24.72× increase in reasoning token consumption, without degrading task performance. Finally, we also discuss and evaluate potential countermeasures to mitigate overthinking risks.

The widespread usage of large-scale multimodal models like CLIP has heightened concerns about the leakage of PII. Existing methods for identity inference in CLIP models require querying the model with full PII, including textual descriptions of the person and corresponding images (e.g., the name and the face photo of the person). However, applying images may risk exposing personal information to target models, as the image might not have been previously encountered by the target model.Additionally, previous MIAs train shadow models to mimic the behaviors of the target model, which incurs high computational costs, especially for large CLIP models. To address these challenges, we propose a textual unimodal detector (TUNI) in CLIP models, a novel technique for identity inference that: 1) only utilizes text data to query the target model; and 2) eliminates the need for training shadow models. Extensive experiments of TUNI across various CLIP model architectures and datasets demonstrate its superior performance over baselines, albeit with only text data.