Apr 26, 2026

Biosecurity Screening Layer for Biology-Oriented AI Interfaces

Adejumobi Joshua, Taiwo Togun

Wittmann et al. (2025) demonstrated that generative protein design tools can produce variants of dangerous toxins that evade existing DNA synthesis screening by preserving biological function while rewriting amino acid sequence — a paraphrase attack. Existing screening systems fail because they rely on sequence similarity, asking does this look like a known toxin? rather than can this do what a toxin does? This project addresses an upstream gap: biology-oriented large language models (LLMs) that can assist users in designing such attacks. We present a four-layer, model-agnostic biosecurity screening system that sits at the interface of biology LLMs and prevents them from being used for protein paraphrase attacks. Our system combines intent detection, LLM-based self-critique, functional toxicity motif analysis, and ESM-2 embedding-based functional similarity scoring. Evaluated using ProLLaMA as the underlying biology LLM, the system blocks 96% of attack prompts while maintaining a 0% false positive rate on legitimate biology queries. Without screening, ProLLaMA answered 100% of attack prompts freely, demonstrating the critical need for this intervention.

Review Project

See Code

View Related Sprint

Reviewer's Comments

This project addresses an important problem with a commendably rigorous approach. However, the current results show only limited success. The intent‑detection layer demonstrates partial effectiveness, as it still struggles to identify evasive prompts that avoid explicit toxin names, which is acknowledged. The function‑based screening using motifs and token embeddings moves in a promising direction, but the present implementation lacks sufficient specificity. Given the constraints of a hackathon timeframe, this effort is appreciated.

Good work for creatively choosing a problem to solve. Models like BioGPT/ProLLaMA are neglected by the biosecurity community and some of your findings here could potentially contribute to safer interfaces with such models. Given their open source nature, though, I'm not sure how tractable solving the uplift-from-bioLLMs problem is.

This is a practical and well-scoped project. You identify a real failure mode in current biosecurity systems and place the defense at a high-leverage point, the LLM interface. The layered design is a strong engineering choice, and the evaluation clearly shows that the intervention changes model behavior in a meaningful way.

The main weakness is confidence in the results. A 96% block rate with 0% false positives suggests the evaluation setup may be too clean. Real users will not submit obvious “attack prompts”. They will obfuscate intent, split tasks across multiple queries, or mix benign and harmful goals.

Also consider system-level limitations. A model-agnostic wrapper is useful, but attackers may bypass the interface entirely or fine-tune their own models. Address where this fits in a broader defense-in-depth strategy. If you can demonstrate robustness under adversarial conditions and clarify the biological validation layer, this could move from a solid engineering solution to a deployable safety system.

Cite this work

@misc {

title={

(HckPrj) Biosecurity Screening Layer for Biology-Oriented AI Interfaces

author={

Adejumobi Joshua, Taiwo Togun

date={

4/26/26

organization={Apart Research},

note={Research submission to the research sprint hosted by Apart.},

howpublished={https://apartresearch.com}

}

Recent Projects

View All

Apr 27, 2026

OliGraph: graph-based screening of large oligopools

Existing synthesis screening tools cannot evaluate short oligonucleotide pools, whose overlapping fragments can be reassembled into regulated sequences via polymerase cycling assembly (PCA) yet fall below gene-length detection thresholds. We present OliGraph, an open-source tool that constructs a bi-directed overlap graph from an oligonucleotide pool and extracts contigs for downstream gene-length screening. An optional PCA mode retains only cross-strand overlaps consistent with PCA chemistry. We validated OliGraph in a blinded study across ten simulated pools (70–9,184 oligonucleotides, 30–300 bp) spanning four risk categories. BLAST screening of individual oligonucleotides failed to identify sequences of concern in most pools: three returned zero hits, and vector noise obscured true positives in the remainder. After OliGraph assembly, contig-level BLAST matched the longest assembled sequences (up to 1,905 bp) to sequences of concern at 97–100% identity. In one pool, assembly collapsed 1,634 individual BLAST results into 10 hits from a single contig, all assigned to the same source organism. PCA mode correctly distinguished assemblable from non-assemblable fragments within the same pool. Two pools with no assemblable structure yielded no contigs. OliGraph processed all pools in under 0.2 seconds, fast enough for real-time order screening and consistent with proposals to bring oligonucleotide orders within the scope of synthesis screening regulation.

Apr 27, 2026

BioRT-Bench: A Multi-Attack Red-Teaming Benchmark for Bio-Misuse Safeguards in Frontier LLMs

Frontier AI laboratories are expected to maintain safeguards against biological misuse, but whether deployed models actually refuse bio-misuse queries under adversarial pressure is largely unmeasured in the public literature. We introduce BioRT-Bench, a benchmark that runs four attack methods (direct request, PAIR, Crescendo, and base64 encoding) against four frontier models (Claude Sonnet 4.6, GPT-5.4, DeepSeek V4-flash, Kimi K2.5) across 40 prompts spanning five biosecurity-relevant categories. Responses are scored by a calibrated judge extending StrongREJECT with two bio-specific dimensions: specificity and actionability. We measure Attack Success Rate (ASR), where 0 means the model fully refused and 1 means it provided specific, actionable bio-misuse content. Our results reveal a sharp robustness divide: Chinese frontier models (DeepSeek, Kimi) have under 5% refusal rates even under direct request (ASR 0.88 and 0.79), while Western models (Claude, GPT) maintain substantially stronger safeguards (ASR 0.15 and 0.16). Crescendo is the most effective attack across all models, both in bypassing refusal and in eliciting actionable content. Claude Sonnet 4.6 is the most robust model tested, achieving 100% refusal against base64-encoded prompts.

Apr 27, 2026

PROTEUS (PROTein Evaluation for Unusual Sequences): Structure-Informed Safety Screening for de novo and Evasion-Prone Protein-Coding Sequences

AI protein design tools like RFdiffusion, ProteinMPNN, and Bindcraft make it trivial to produce low-homology sequences that fold into active, potentially hazardous architectures. However, sequence homology-based biosafety screening tools cannot detect proteins that pose functional risk through structurally novel mechanisms with no sequence precedent. We present a tiered computational pipeline that addresses this gap by combining MMseqs2 sequence alignment with structure-based comparison via FoldSeek and DALI against curated toxin databases totaling ~34,000 entries. AlphaFold2-predicted structures are screened for both global fold similarity (FoldSeek) and local active/allosteric site geometry (DALI), capturing convergent functional hazards that sequence screening misses. The pipeline was validated against a panel of toxins, benign proteins, structural mimics, and de novo-designed Munc13 binders, as well as modified ricin variants with residue substitutions. We additionally tested robustness to partial-synthesis evasion, where a bad actor submits multiple shorter coding sequences intended for downstream reassembly into a full toxin-coding gene. We found that while sequence-based screening did not identify any de novo ricin analogues with high certainty, the combined pipeline with FoldSeek and DALI identified all 24 tested de novo ricins as toxic.

Apr 27, 2026