arXiv AI August 6, 2026 By Prashant Kulkarni, Assaf Namer

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models

arXiv:2503. 15560v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build context through seemingly benign conversational turns to circumvent safety measures and elicit harmful or unauthorized responses.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

1d ago

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.

By Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu, Ruihong Huang

llms robotics fine-tuning multimodal benchmarks safety

arXiv AI

Jul 14

Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message

arXiv:2507. 04673v2 Announce Type: replace Abstract: The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue history for sophisticated reasoning.

By Wei Duan, Li Qian

llms multimodal safety

arXiv AI

Jul 14

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents

arXiv:2605. 01143v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning.

By Sheldon Yu, Yingcheng Sun, Hanqing Guo, Qianqian Tong

llms agents benchmarks safety

arXiv Machine Learning

Aug 4

Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs

arXiv:2601. 14340v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as multi-turn assistants and customized through instruction tuning with project-specific training components.

By Yiyang Lu, Jinwen He, Yue Zhao, Kai Chen, Ruigang Liang, Cheng Hong, Yingjun Zhang

llms fine-tuning

arXiv AI

Aug 11

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).

By Adarsh Kumarappan, Ananya Mujoo

llms robotics multimodal benchmarks safety

arXiv AI

Jun 19

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

arXiv:2606. 20470v1 Announce Type: cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.

By Reza Soosahabi, Vivek Namsani

agents multimodal benchmarks safety

Related stories

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents

Turn-Based Structural Triggers: Structure-Conditioned Backdoors in Multi-Turn LLMs

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems