Parallax: Why AI Agents That Think Must Never Act

• URL: http://arxiv.org/abs/2604.12986v1
• Date: Tue, 14 Apr 2026 17:20:48 GMT
• Title: Parallax: Why AI Agents That Think Must Never Act
• Abstract summary: This paper introduces Parallax, a paradigm for safe autonomous AI execution grounded in four principles.<n>We present OpenParallax, an open-source reference implementation in Go, and evaluate it usingAssume-Compromise Evaluation.<n>Across 280 adversarial test cases in nine attack categories, Parallax blocks 98.9% of attacks with zero false positives under its default configuration, and 100% of attacks under its maximum-security configuration.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise applications will embed AI copilots by the end of 2026. As agents gain the ability to execute real-world actions (reading files, running commands, making network requests, modifying databases), a fundamental security gap has emerged. The dominant approach to agent safety relies on prompt-level guardrails: natural language instructions that operate at the same abstraction level as the threats they attempt to mitigate. This paper argues that prompt-based safety is architecturally insufficient for agents with execution capability and introduces Parallax, a paradigm for safe autonomous AI execution grounded in four principles: Cognitive-Executive Separation, which structurally prevents the reasoning system from executing actions; Adversarial Validation with Graduated Determinism, which interposes an independent, multi-tiered validator between reasoning and execution; Information Flow Control, which propagates data sensitivity labels through agent workflows to detect context-dependent threats; and Reversible Execution, which captures pre-destructive state to enable rollback when validation fails. We present OpenParallax, an open-source reference implementation in Go, and evaluate it using Assume-Compromise Evaluation, a methodology that bypasses the reasoning system entirely to test the architectural boundary under full agent compromise. Across 280 adversarial test cases in nine attack categories, Parallax blocks 98.9% of attacks with zero false positives under its default configuration, and 100% of attacks under its maximum-security configuration. When the reasoning system is compromised, prompt-level guardrails provide zero protection because they exist only within the compromised system; Parallax's architectural boundary holds regardless.

Related papers

• HazardAuditor: From Executable Threats to Safer Computer-Use Agents [50.06351661912873]
  Existing guard models target static prompts and responses.<n>Existing safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn.<n>We introduce HazardAuditor, an execution-grounded framework that closes both gaps.
  arXiv  Detail & Related papers  (2026-09-14T07:09:33Z)
• Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents [93.19140872946842]
  Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments.<n>This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour.<n>We introduce textbfsysname, a benchmark to systematically categorize and attribute harm in real-world web agent systems.
  arXiv  Detail & Related papers  (2026-06-11T14:12:43Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents [43.702131498259384]
  This paper systematically investigates Tool Description Poisoning (TDP), a novel semantic attack.<n>In TDP, malicious instructions are not embedded in a tool's executable code, but rather covertly injected into its descriptive metadata.<n>This work provides the first specialized security benchmark tailored for TDP, offering essential insights for securing the cognitive and planning layers of advanced agentic systems.
  arXiv  Detail & Related papers  (2026-05-22T08:34:48Z)
• PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification [1.7904458681854372]
  PlanGuard is a training-free defense framework based on the principle of Context Isolation.<n>PlanGuard effectively neutralizes attacks, reducing the Attack Success Rate (ASR) from 72.8% to 0%.
  arXiv  Detail & Related papers  (2026-04-11T09:59:46Z)
• CORA: Conformal Risk-Controlled Agents for Safeguarded Mobile GUI Automation [68.53387633351484]
  We propose CORA (COnformal Risk-controlled GUI Agent), a post-policy, pre-action safeguarding framework that provides statistical guarantees on harmful executed actions.<n> CORA reformulates safety as selective action execution: we train a Guardian model to estimate action-conditional risk for each proposed step.<n>To rigorously evaluate this paradigm, we introduce Phone-Harm, a new benchmark of mobile safety violations with step-level harm labels.
  arXiv  Detail & Related papers  (2026-04-10T09:41:21Z)
• CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents [27.35968236632966]
  LLM-based code interpreter agents are increasingly deployed in critical situations.<n>Existing benchmarks fail to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context.<n>We introduce CIBER, an automated benchmark that combines dynamic attack generation, isolated secure sandboxing, and state-aware evaluation.
  arXiv  Detail & Related papers  (2026-02-23T06:41:41Z)
• Authenticated Workflows: A Systems Approach to Protecting Agentic AI [0.0]
  We introduce authenticated, the first complete trust layer for enterprise agentic AI.<n>We enforce intent (operations satisfy organizational policies) and integrity (operations are cryptographically authentic) at every boundary crossing.<n>This delivers deterministic security--operations either carry valid cryptographic proof or are rejected.
  arXiv  Detail & Related papers  (2026-02-11T03:04:50Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)
• Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous Execution [1.3537117504260623]
  This paper presents a Fault-Tolerant Sandboxing framework designed to mitigate these risks.<n>We hypothesize that wrapping agent actions in atomic transactions can guarantee safety with acceptable latency.<n> Experimental results demonstrate a 100% interception rate for high-risk commands and a 100% success rate in rolling back failed states.
  arXiv  Detail & Related papers  (2025-12-14T19:03:59Z)
• Cognitive Control Architecture (CCA): A Lifecycle Supervision Framework for Robustly Aligned AI Agents [1.014002853673217]
  LLM agents are vulnerable to Indirect Prompt Injection (IPI) attacks.<n>IPI attacks hijack agent behavior by polluting external information sources.<n>We propose the Cognitive Control Architecture (CCA), a holistic framework achieving full-lifecycle cognitive supervision.
  arXiv  Detail & Related papers  (2025-12-07T08:11:19Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.