Preetha Chatterjee

🌍 The future of #icse is global!
🇧🇷 ICSE 2026 – Brazil #icse2026
🇮🇪 ICSE 2027 – Ireland #icse2027
🌺 ICSE 2028 – Hawaii #icse2028
We can't wait to see you there! Pack your ideas and your passport. 🧳✈️

02.05.2025 13:24 — 👍 15    🔁 9    💬 1    📌 1

💡 If you are building, evaluating, or relying on LLMs for software development, please ask yourself: Did it warn you about the hidden security risk?

07.04.2025 13:43 — 👍 0    🔁 0    💬 0    📌 0

As a preliminary solution to this problem, we built a CLI tool prototype that integrates static analysis with LLM prompting, aiming to make AI code suggestions more secure by design.

07.04.2025 13:43 — 👍 0    🔁 0    💬 1    📌 0

However, when LLMs do warn you, they tend to offer more complete explanations, including potential causes of the vulnerability, exploits, and even fixes.

07.04.2025 13:43 — 👍 0    🔁 0    💬 1    📌 0

We evaluated GPT-4, Claude 3, and Llama 3 across 300 real-world Stack Overflow posts containing vulnerable code.

The results?
⚠️<40% of vulns flagged
⚠️As low as 12.6% when code was obfuscated
⚠️Common issues (e.g., unsanitized input) often missed - unless explicitly prompted

07.04.2025 13:43 — 👍 0    🔁 0    💬 1    📌 0

Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions The widespread adoption of conversational LLMs for software development has raised new security concerns regarding the safety of LLM-generated content. Our motivational study outlines ChatGPT's potent...

LLMs are great at generating code, but are they silently spreading vulnerabilities? TLDR: Yes.

In our latest EMSE paper, we look into: when developers unknowingly share vulnerable code with LLMs, do these models proactively raise security red flags? 🧵

👉 Read the paper: arxiv.org/abs/2502.14202

07.04.2025 13:42 — 👍 2    🔁 0    💬 1    📌 0

Delighted to share that our paper, led by my PhD advisee Ramtin Ehsani, “Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution,” has been accepted to the Research Track of MSR 2025.

Preprint: soar-lab.github.io//papers/MSR2...

21.01.2025 02:17 — 👍 3    🔁 0    💬 0    📌 0

I can now run a GPT-4 class model on my laptop Meta’s new Llama 3.3 70B is a genuinely GPT-4 class Large Language Model that runs on my laptop. Just 20 months ago I was amazed to see something that felt …

I can now run a GPT-4 class model on my laptop

(The exact same laptop that could just about run a GPT-3 class model 20 months ago)

The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years
simonwillison.net/2024/Dec/9/l...

09.12.2024 15:19 — 👍 361    🔁 59    💬 11    📌 6

Congrats!!

10.12.2024 14:59 — 👍 1    🔁 0    💬 0    📌 0

#NeurIPS2024 paper 3, Assemblage - the dataset of source-to-binary projects compiled from GitHub that you've dreamed of bet never had before! Collab with @krismicinski.bsky.social and a multi-year effort to get to @NeurIPSConf @BoozAllen arxiv.org/abs/2405.03991

07.12.2024 20:01 — 👍 6    🔁 3    💬 1    📌 0

🎉 Thrilled to share that our paper (with Ramtin Ehsani and @rezapour.bsky.social) has been accepted at NLBSE'25, co-located with @icseconf.bsky.social! 🎉

Our work shows promise in improving toxicity detection in OSS using moral values & psycholinguistic cues. Preprint coming soon.

09.12.2024 16:42 — 👍 3    🔁 2    💬 0    📌 0

Can you please add me here

23.11.2024 03:28 — 👍 1    🔁 0    💬 0    📌 0