THRD introduces a novel, training-free framework that models temporal risk accumulation to effectively defend against multi-turn jailbreak attacks on LLMs, significantly reducing attack success rates…

The paper introduces TurnGate, a response-aware defense mechanism that detects the earliest turn in a multi-turn dialogue where the accumulated interaction enables a harmful action, significantly impr…

The paper introduces MT-JailBench, a modular framework for evaluating multi-turn jailbreaks, demonstrating that controlling experimental components like prompt generation and resource budgets is cruci…

The paper introduces Transient Turn Injection (TTI), a novel multi-turn attack technique that exploits stateless moderation in LLMs by distributing adversarial intent across isolated interactions, rev…

The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.

The paper proposes mitigating the progressive degradation of safety in language models caused by many-shot jailbreak attacks by appending a single, fixed safety demonstration at inference time.

CivicShield introduces a novel, seven-layered defense-in-depth framework that significantly enhances the security of government-facing AI chatbots against sophisticated multi-turn adversarial attacks.

The paper proposes an unsupervised bi-level adversarial training framework to enhance LLM safety steering, achieving strong zero-shot defense against unseen and evolving jailbreak prompts.

This paper addresses the lack of systematic infrastructure for evaluating jailbreak attacks by introducing a large-scale dataset, an automated generation method, and a continuous evaluation metric tha…

This paper argues that reporting only the best-case attack success rate for jailbreaks is insufficient, proposing new distributional metrics (VSM and UC) to better characterize the true threat posed b…

The paper introduces Disrupt-and-Rectify Smoothing (DR-Smoothing), a novel two-stage defense mechanism that significantly improves LLM security against jailbreaking attacks by restoring disrupted inpu…

The paper introduces Salami Slicing Risk, a novel multi-turn jailbreak technique that accumulates harmful intent through numerous low-risk inputs, achieving state-of-the-art attack success rates again…

The paper introduces Temporal Logit Observability (TLO), a training-free diagnostic that analyzes the decoding process to reveal the temporal patterns of LLM safety failures, showing that failure mech…

TwinGate introduces a stateful dual-encoder defense framework using Asymmetric Contrastive Learning to detect malicious intent from fragmented, untraceable LLM queries with high recall and low false p…

SAFEDREAM introduces a lightweight, external world-model framework that proactively detects multi-turn jailbreak attacks by modeling cumulative safety erosion and predicting early failure points.

This paper introduces Security Cube, a comprehensive, multi-dimensional framework for evaluating LLM robustness against jailbreak attacks, providing a systematic taxonomy and benchmark analysis of exi…

The paper proposes Ellipsoid Control, a white-list defense mechanism that uses benign data geometry to constrain model updates, thereby enhancing jailbreak safety while preserving the utility of harml…

The paper introduces PsychoPass, a framework that analyzes the geometric trajectory of multi-turn conversations in embedding space to detect adversarial intent early, before harmful content is generat…

D-Judge introduces a semantics-preserving output rewriting defense that disrupts multi-turn jailbreak attacks by misaligning the feedback signal used by an attacker's judge model.

NeuroArmor is a white-box runtime defense that uses prompt-specific safe variants to selectively detect and mitigate jailbreak attacks, significantly reducing attack success rates while maintaining a…