SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI

• URL: http://arxiv.org/abs/2607.22926v1
• Date: Fri, 24 Jul 2026 21:36:28 GMT
• Title: SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI
• Abstract summary: SAGE is a safety-first, authorization-separated architecture.<n>It combines signed release manifests, diverse detectors, robust risk envelopes, least-risk defaults, output checking, protected audit chains, containment, and rollback.<n>Formal results establish safety priority, conservative detector bounds, monotone release gating, tamper-evident records, and an authorization cut.
• Score: 0.152292571922932
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem. SAGE is a safety-first, authorization-separated architecture in which credible catastrophic-enablement risk constrains admissibility before utility, latency, or commercial objectives are considered. It combines signed release manifests, diverse detectors, robust risk envelopes, least-risk defaults, output checking, three-valued monitoring, protected audit chains, containment, and rollback. Formal results establish safety priority, conservative detector bounds, monotone release gating, tamper-evident records, and an authorization cut; two PRISM abstractions verify authorization separation and lifecycle invariants under explicit assumptions. A frozen, vendor-symmetric study sent 84 cases to each of four GPT, four Claude, and two Gemini snapshots: 840 calls yielded 794 target responses, 46 provider errors, and 449 successful judgments covering 375 responses. Eight snapshots had complete judged domain coverage. Harmful-compliance estimates were low; variation arose mainly from benign utility and safe redirection. Seven multiplicity-adjusted contrasts involving Claude, Gemini, or GPT-5 snapshots and the GPT-5 mini and GPT-5 nano snapshots were supported, while no tested contrast between the Claude or Gemini snapshots and GPT-5 or GPT-5.5 survived correction. The observed harmful-compliance range is a conservative, protocol-bound view from one generation per prompt with no tools, retrieval, history, or human adjudication; it is not an upper bound on operational assistance. A preregistered extension specifies how to test a wider best-worst gap using a locked split, repeated sampling, multi-turn and sandboxed-tool conditions, and domain-expert scoring.

Related papers

• SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration [4.906746849209501]
  Industrial inspection pipelines often restore a measured image before a detector acts on it, yet restoration can suppress detector-supported defect structure or create clean-region activations.<n>We formulate restoration as a selective action problem over the measured display, five restored candidates, and review.<n>SafeRestore ranks candidates with action-specific fitted scores, chooses a gate on threshold-tuning data, and evaluates the fixed gate on a disjoint certification sample with two one-sided exact binomial bounds.
  arXiv  Detail & Related papers  (2026-09-03T07:32:42Z)
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle [65.6642776933861]
  This survey examines the protective paradigm that has grown around this intervention point.<n>We find that most protections are still validated mainly against static or weakly adaptive adversaries.<n>We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.
  arXiv  Detail & Related papers  (2026-08-05T00:46:50Z)
• Auditable Release Control for Pedagogical Leakage in LLM Tutors [0.0]
  Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning before that disclosure is authorized.<n>We formalize this state- and action-dependent failure as pedagogical leakage-aware authorization and introduce complete-mediation boundary.<n>A global A1 yields 0 majority and 54 any-utility flags, outperforming fitted Q on automatic safety and utility.
  arXiv  Detail & Related papers  (2026-08-01T08:24:30Z)
• Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense [37.10272384523361]
  We develop a framework for predicting each detector's per-sample reliability and latency from how it behaved on similar past inputs.<n>We build SCOUT-450, a benchmark that captures the structurally complex, agent-facing injections that older prompt-injection sets under-represent.<n>On SCOUT-450, a safety-oriented operating point reduces attack-success rate by 46% and total wall-clock by 40% relative to an always-on GPT-4o judge.
  arXiv  Detail & Related papers  (2026-05-29T04:49:20Z)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• Acceptance Cards:A Four-Diagnostic Standard for Safe Fine-Tuning Defense Claims [0.6882042556551609]
  We introduce Acceptance Cards: an evaluation protocol, a documentation object, an executable audit package, and a claim-specific evidential standard for safe fine-tuning defense claims.<n>The protocol checks statistical reliability, fresh semantic generalization, mechanism alignment, and cross-task transfer before treating a gap reduction as a full-card pass.<n>This is a narrow installed-gap audit on one model family, not a global judgment of SafeLoRA's effectiveness.
  arXiv  Detail & Related papers  (2026-05-11T13:48:42Z)
• Affordance Agent Harness: Verification-Gated Skill Orchestration [45.231685718099264]
  Affordance grounding requires identifying where and how an agent should interact in open-world scenes.<n>We propose Affordance Agent Harness, a closed-loop runtime that unifies skills with an evidence store and cost control.
  arXiv  Detail & Related papers  (2026-05-01T13:45:16Z)
• TRUST: A Framework for Decentralized AI Service v.0.1 [47.384270414446604]
  Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification.<n>We introduce TRUST (Transparent, Robust, and Unified Services for Trustworthy AI), a decentralized framework with three innovations.<n>We prove a Safety-Profitability Theorem ensuring honest auditors profit while malicious actors incur losses.
  arXiv  Detail & Related papers  (2026-04-29T19:32:58Z)
• Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors [48.881343993730844]
  Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines.<n> adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present.<n>Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors.
  arXiv  Detail & Related papers  (2026-04-14T06:48:33Z)
• Broken by Default: A Formal Verification Study of Security Vulnerabilities in AI-Generated Code [0.0]
  Broken by Default is a formal verification study of 3,500 code artifacts generated by seven widely-deployed LLMs across 500 security-critical prompts.<n>Across all models, 55.8% of artifacts contain at least one COBALT-identified vulnerability; of these, 1,055 are formally proven via Z3 satisfiability witnesses.<n>GPT-4o leads at 62.4% (grade F); Gemini 2.5 Flash performs best at 48.4% (grade D)
  arXiv  Detail & Related papers  (2026-04-07T00:55:42Z)
• TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol [1.0195618602298684]
  TraceGuard is a structured multi-dimensional monitoring protocol that evaluates agent actions across five dimensions.<n>It is implemented as a new monitor type for the open-source ControlArena framework.
  arXiv  Detail & Related papers  (2026-04-05T05:05:59Z)
• Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away [97.11976870616273]
  We propose a lightweight inference-time defense that treats safety recovery as a satising constraint rather than an objective.<n>In our evaluations across six open-source MLRMs and four jailbreak benchmarks, SafeThink reduces attack success rates by 30-60%.
  arXiv  Detail & Related papers  (2026-02-11T18:09:17Z)
• ProGuard: Towards Proactive Multimodal Safeguard [48.89789547707647]
  ProGuard is a vision-language proactive guard that identifies and describes out-of-distribution (OOD) safety risks.<n>We first construct a modality-balanced dataset of 87K samples, each annotated with both binary safety labels and risk categories.<n>We then train our vision-language base model purely through reinforcement learning to achieve efficient and concise reasoning.
  arXiv  Detail & Related papers  (2025-12-29T16:13:23Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• GSAE: Graph-Regularized Sparse Autoencoders for Robust LLM Safety Steering [5.124731939041066]
  Large language models (LLMs) face critical safety challenges as they can be manipulated to generate harmful content through adversarial prompts and jailbreak attacks.<n>We introduce Graph-Regularized Sparse Autoencoders (GSAEs), which extends SAEs with a Laplacian smoothness penalty on the neuron co-activation graph.<n>We demonstrate that GSAE enables effective safety steering, assembling features into a weighted set of safety-relevant directions and controlling them with a two-stage gating mechanism.
  arXiv  Detail & Related papers  (2025-12-07T04:46:30Z)
• Multimodal Safety Evaluation in Generative Agent Social Simulations [43.972551727499116]
  We introduce a reproducible simulation framework for evaluating agents along three dimensions.<n>We show that agents often fail to align local revisions with global safety, reaching only a 55 percent success rate in correcting unsafe plans.<n> Notably, 45 percent of unsafe actions were accepted when paired with misleading visuals, showing a strong tendency to overtrust images.
  arXiv  Detail & Related papers  (2025-10-09T02:42:57Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)

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.