# STACK: Adversarial Attacks on LLM Safeguard Pipelines

arXiv: https://arxiv.org/abs/2506.24068 · HTML: https://mlsanity.com/paper/2506.24068/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 30 of 37)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [ShieldGemma: Generative AI Content Moderation Based on Gemma](https://mlsanity.com/paper/2407.21772/) (2024)
- [Jailbreak Attacks and Defenses Against Large Language Models: A Survey](https://mlsanity.com/paper/2407.04295/) (2024)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming](https://mlsanity.com/paper/2501.18837/) (2025)
- [Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs](https://mlsanity.com/paper/2407.15549/) (2024)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Fast Adversarial Attacks on Language Models In One GPU Minute](https://mlsanity.com/paper/2402.15570/) (2024)
- [Defending Against Unforeseen Failure Modes with Latent Adversarial Training](https://mlsanity.com/paper/2403.05030/) (2024)
- [Trading Inference-Time Compute for Adversarial Robustness](https://mlsanity.com/paper/2501.18841/) (2025)
- [PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails](https://mlsanity.com/paper/2402.15911/) (2024)

## Built on by (most cited first, 14 of 14)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG](https://mlsanity.com/paper/2510.09710/) (2025)
- [Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs](https://mlsanity.com/paper/2512.05648/) (2025)
- [Boundary Point Jailbreaking of Black-Box LLMs](https://mlsanity.com/paper/2602.15001/) (2026)
- [REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems](https://mlsanity.com/paper/2608.10669/) (2026)
- [Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models](https://mlsanity.com/paper/2603.11149/) (2026)
- [Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands](https://mlsanity.com/paper/2605.15164/) (2026)
- [Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs](https://mlsanity.com/paper/2606.17110/) (2026)
- [AI Security Leaderboard: Methodology, Results and Minimal Standard](https://mlsanity.com/paper/2608.03070/) (2026)
- [Directional Embedding Smoothing for Robust Vision Language Models](https://mlsanity.com/paper/2603.15259/) (2026)
- [On the Hardness of Junking LLMs](https://mlsanity.com/paper/2605.05116/) (2026)
- [A Systematic Investigation of RL-Jailbreaking in LLMs](https://mlsanity.com/paper/2605.07032/) (2026)
- [Sharding Prevents LLM Oversight Failures and Adversarial Exploitation](https://mlsanity.com/paper/2608.06422/) (2026)
- [Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection](https://mlsanity.com/paper/2609.24801/) (2026)

## Abstract (arXiv)

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic and OpenAI guard their latest Opus 4 model and GPT-5 models using such defense pipelines, and other frontier developers including Google DeepMind pledge to soon deploy similar defenses. However, the security of such pipelines is unclear, with limited prior work evaluating or attacking these pipelines. We address this gap by developing and red-teaming an open-source defense pipeline. First, we find that a novel few-shot-prompted input and output classifier outperforms state-of-the-art open-weight safeguard model ShieldGemma across three attacks and two datasets, reducing the attack success rate (ASR) to 0% on the catastrophic misuse dataset ClearHarm. Second, we introduce a STaged AttaCK (STACK) procedure that achieves 71% ASR on ClearHarm in a black-box attack against the few-shot-prompted classifier pipeline. Finally, we also evaluate STACK in a transfer setting, achieving 33% ASR, providing initial evidence that it is feasible to design attacks with no access to the target pipeline. We conclude by suggesting specific mitigations that developers could use to thwart staged attacks.