arXiv AI July 1, 2026 By Mitchell Hermon, Rahul Gupta, Weitong Ruan, Ekraam Sabir, Haohan Wang

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

arXiv:2606. 30783v1 Announce Type: cross Abstract: We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which corrupts tasks that must preserve it, such as translation and document editing.

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

arXiv Machine Learning

Jun 18

Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks

arXiv:2606. 18530v1 Announce Type: cross Abstract: Domain-camouflaged injection attacks embed malicious instructions in retrieved content using domain-appropriate vocabulary, evading standard detectors that rely on syntactic injection markers.

By Aaditya Pai

llms agents benchmarks

arXiv AI

Jun 29

On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models

arXiv:2606. 27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken.

By Dewank Pant, Shruti Lohani, Avijit Kumar

llms rag safety

arXiv AI

Jul 31

Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

arXiv:2607. 26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate.

By Haoyu Zhang, Shibo Zheng, Xiangchen Guan, Zhuoxi Wang, Zijian Xiao, Mohammad Zandsalimy, Shanu Sushmita

safety

arXiv AI

Jun 12

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.

By Zihao Wang, Yiming Li, Yutong Wu, Zheyu Liu, Kangjie Chen, Fok Kar Wai, Pin-Yu Chen, Vrizlynn L. L. Thing, Bo Li, Dacheng Tao, Tianwei Zhang

llms agents benchmarks safety

arXiv AI

Jun 16

AutoDojo: Adaptive Attacks Expose Superficial Defenses and User-Underspecification Limits in LLM Agents

arXiv:2606. 15057v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents.

By Xinhang Ma, Taoran Li, Chaowei Xiao, Zhiyuan Yu, Ning Zhang, Yevgeniy Vorobeychik

llms agents multimodal benchmarks

arXiv Machine Learning

Aug 11

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes

arXiv:2608. 08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data.

By Laiqiao Qin, Tianqing Zhu, Longxiang Gao, Wanlei Zhou

llms rag

Related stories

Evaluating Prompting-Based Defenses Against Domain-Camouflaged Injection Attacks

On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models

Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

AutoDojo: Adaptive Attacks Expose Superficial Defenses and User-Underspecification Limits in LLM Agents

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes