AI & ML
PIPETTE: Prompt Injection Purple-Teaming for Robust LLM Agents
arXiv cs.CR0 views
arXiv:2611.24362v1 Announce Type: new Abstract: Large language model (LLM) agents routinely interact with untrusted external data, exposing them to indirect prompt injection (IPI) attacks that hijack agents into executing attacker-chosen tasks. To uncover these vulnerabilities at scale, automated red-teaming methods often leverage reinforcement learning (RL) to generate attacks that achieve high attack success rates (ASR). Model developers use the attacks discovered during internal red-teaming to harden agents through adversarial training before deployment, a collaborative offensive-defensive process known in cybersecurity as purple-teaming. However, we show that achieving high ASR during red-teaming does not guarantee robustness gains from subsequent adversarial training. Specifically, we find that two state-of-the-art RL-based red-teaming methods, RL-Hammer and PISmith, suffer from mode collapse, repeatedly discovering similar attack strategies whose additional successes add no additional robustness improvements to adversarial training. To address this gap, we introduce PIPETTE, a unified prompt injection purple-teaming framework that effectively converts red-teaming discoveries into defender robustness improvements. PIPETTE employs a dictionary learning-based reward that encourages broader coverage of attack strategies during red-teaming. It also integrates an on-policy adversarial training pipeline tailored to IPI defense, enabling agents to resist attacks while completing legitimate user tasks. Extensive evaluations across agentic benchmarks (AgentDojo and ASB) demonstrate that PIPETTE produces defenders that achieve near-zero attack success rates on static attacks and can withstand strong adaptive attacks, while maintaining benign task utility close to that of the undefended baseline.
Source:https://arxiv.org/abs/2611.24362PreviousAutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM AgentsNextA Differential Theory of Quality-Resource Trade-offs for AI Model Selection: The Multiresource Frontier and Its Minimax Price
Related posts
Ruby2ßhell: Pre-authentication RCE on stock Rails
0Hacker News
Generalizing self-normalized importance sampling with couplings
0arXiv stat.CO
Bayesian Computation of Copula-based Multivariate Models with an Application to Doping Detection
0arXiv stat.CO
WAIVES: Weak-form Asymptotically-unbiased Instrumental-Variable Estimation for SDEs
0arXiv stat.CO
Treat Your Honeypot Analysis Like Code: Git, Pull Requests and a Human Gate for AI [Guest Diary], (Wed, Nov 18th)
0SANS ISC
ISC Stormcast For Thursday, November 19th, 2026 https://isc.sans.edu/podcastdetail/10186, (Thu, Nov 19th)
0SANS ISC