Reflex-Guard is introduced, a lightweight guardrail that runs locally that uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers that enable high-accuracy prompt safety filtering with much lower latency than existing solutions.
Abstract
Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers. Together, these components enable high-accuracy prompt safety filtering with much lower latency than existing solutions. Through systematic evaluation on a strategically balanced dataset of 30,568 samples drawn from five complementary sources, we demonstrate that Reflex-Guard achieves 95.9% recall on harmful prompts at 37.6 ms end-to-end latency. It is faster than existing baselines, including Llama Guard 2 at 255 ms and SafeDecoding at 723 ms. It can detect 100% of GCG suffix attacks and Base64-encoded prompts using the default threshold. However, DrAttack structured prompts required lowering the threshold to 0.03 for optimal detection, as they produced a distinct probability distribution. Reflex-Guard achieves Reflex Efficiency Score (RES) scores up to 16.79, significantly outperforming Llama Guard 2 (11.90) and SafeDecoding (9.80). This analysis offers practical deployment advice and shows that different attack types occupy distinct regions in the embedding probability space.
Current safety guard models for Large Language Models (LLMs) often fail to block complex Jailbreaking attacks because they focus on the structure of a prompt rather than its true intent. To evaluate this problem, we introduce the Role-Goal-Format (RGF) framework, which analyzes how the combination of a user’s persona, their objective, and the text format can bypass safety filters. We compared two small safety guard models: Prompt Guard 2 and Llama Guard 3. The results show that even with the same overall accuracy, they have completely opposite weaknesses. Prompt Guard 2 is easily bypassed by unusual text formats. On the other hand, Llama Guard 3 lacks semantic understanding, missing 76.7% of virus-related attacks. Furthermore, both models exhibit a common vulnerability to contextual breaking; they fail to activate safety alignment when harmful objectives are framed within authoritative and benign personas, such as Teacher, Engineer, and Investigator. These findings highlight that small safety guard models have clear limitations and require multi-layered defenses that understand both text structure and actual intent.
Jin-Seong Kim, Han-Ju Lee, Hyeon-Jin Jeong et al.· International Conference on...· 0 citations
Experiments across three instruction-tuned models show that HiRoute achieves high safety rates across multiple safety benchmarks while preserving safe-response helpfulness, reducing over-refusal, and maintaining competitive performance on general-purpose tasks.
Fangzhou Chen, Shiji Zhao, Mengyan Wang et al.· 0 citations
BERM is introduced, a lightweight framework that performs in-situ detection by modeling a host LLM’s internal representations extracted during prefill, adding negligible overhead and reducing incremental inference overhead to near-zero.
Large language models (LLMs) embedded in enterprise workflows cannot structurally distinguish legitimate instructions from adversarial ones in the same token stream, making prompt injection OWASP's top LLM risk for two consecutive editions a persistent threat across direct and indirect vectors. This paper presents PromptShield-RT, a layered, real-time, model-agnostic framework combining input normalization and provenance tagging, lexical-heuristic pattern matching, a statistical classifier, structural anomaly features, and calibrated risk fusion, with policy-driven mitigation (allow/sanitize/quarantine/block) and an explainable, adaptive-feedback mechanism for SOC workflows. We construct an original evaluation corpus, SynPI-Bench (n = 450, six categories), and a template-disjoint held-out generalization set (n = 31) with novel phrasings, obfuscation encodings, and adversarial hard-negative benign text. Using template-grouped 5-fold cross-validation, the fused pipeline achieves 92.4% accuracy (F1 = 0.930, AUC = 0.990), outperforming heuristic-only (57.0%) and naive-averaged (59.2%) baselines, while a lexical classifier reaches 85.9% with lower precision. We report a pronounced generalization gap on the held-out set (48.4% accuracy, 90% false-positive rate on hard negatives), quantifying a known limitation of surface-lexical defenses. The pipeline achieves sub-millisecond P95 latency (0.266 ms), within typical 50 ms enterprise SLAs. We situate PromptShield-RT relative to structural, architectural, and guardrail-product defenses, arguing for layered, defense-in-depth architectures, with reproducible code provided.
Fatimah Alhamzawi· Al-Noor Journal of Engineeri...· 0 citations
It is suggested that multimodal safety cannot be enforced reliably without modeling the requested operation, the visual target to which it applies, and the confidence of that grounding.
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
MIT News · Artificial Intelligence· news.mit.eduAug 18, 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
