AI

Lakera launches to protect large language models from malicious prompts

Comment

Chat with AI
Image Credits: Supatman / Getty Images

Large language models (LLMs) are the driving force behind the burgeoning generative AI movement, capable of interpreting and creating human-language texts from simple prompts — this could be anything from summarizing a document to writing a poem to answering a question using data from myriad sources.

However, these prompts can also be manipulated by bad actors to achieve far more dubious outcomes, using so-called “prompt injection” techniques whereby an individual inputs carefully crafted text prompts into an LLM-powered chatbot with the purpose of tricking it into giving unauthorized access to systems, for example, or otherwise enabling the user to bypass strict security measures.

And it’s against that backdrop that Swiss startup Lakera is officially launching to the world today, with the promise of protecting enterprises from various LLM security weaknesses such as prompt injections and data leakage. Alongside its launch, the company also revealed that it raised a hitherto undisclosed $10 million round of funding earlier this year.

Data wizardry

Lakera has developed a database comprising insights from various sources, including publicly available open source datasets, its own in-house research and — interestingly — data gleaned from an interactive game the company launched earlier this year called Gandalf.

With Gandalf, users are invited to “hack” the underlying LLM through linguistic trickery, trying to get it to reveal a secret password. If the user manages this, they advance to the next level, with Gandalf getting more sophisticated at defending against this as each level progresses.

Lakera's Gandalf
Lakera’s Gandalf. Image Credits: TechCrunch
Image Credits: Lakera

Powered by OpenAI’s GPT3.5, alongside LLMs from Cohere and Anthropic, Gandalf — on the surface, at least — seems little more than a fun game designed to showcase LLMs’ weaknesses. Nonetheless, insights from Gandalf will feed into the startup’s flagship Lakera Guard product, which companies integrate into their applications through an API.

“Gandalf is literally played all the way from like six-year-olds to my grandmother, and everyone in between,” Lakera CEO and co-founder David Haber explained to TechCrunch. “But a large chunk of the people playing this game is actually the cybersecurity community.”

Haber said the company has recorded some 30 million interactions from 1 million users over the past six months, allowing it to develop what Haber calls a “prompt injection taxonomy” that divides the types of attacks into 10 different categories. These are: direct attacks; jailbreaks; sidestepping attacks; multi-prompt attacks; role-playing; model duping; obfuscation (token smuggling); multi-language attacks; and accidental context leakage.

From this, Lakera’s customers can compare their inputs against these structures at scale.

“We are turning prompt injections into statistical structures — that’s ultimately what we’re doing,” Haber said.

Prompt injections are just one cyber risk vertical Lakera is focused on though, as it’s also working to protect companies from private or confidential data inadvertently leaking into the public domain, as well as moderating content to ensure that LLMs don’t serve up anything unsuitable for kids.

“When it comes to safety, the most popular feature that people are asking for is around detecting toxic language,” Haber said. “So we are working with a big company that is providing generative AI applications for children, to make sure that these children are not exposed to any harmful content.”

Lakera Guard
Lakera Guard. Image Credits: Lakera
Image Credits: Lakera

On top of that, Lakera is also addressing LLM-enabled misinformation or factual inaccuracies. According to Haber, there are two scenarios where Lakera can help with so-called “hallucinations” — when the output of the LLM contradicts the initial system instructions, and where the output of the model is factually incorrect based on reference knowledge.

“In either case, our customers provide Lakera with the context that the model interacts in, and we make sure that the model doesn’t act outside of those bounds,” Haber said.

So really, Lakera is a bit of a mixed bag spanning security, safety and data privacy.

EU AI Act

With the first major set of AI regulations on the horizon in the form of the EU AI Act, Lakera is launching at an opportune moment in time. Specifically, Article 28b of the EU AI Act focuses on safeguarding generative AI models through imposing legal requirements on LLM providers, obliging them to identify risks and put appropriate measures in place.

In fact, Haber and his two co-founders have served in advisory roles to the Act, helping to lay some of the technical foundations ahead of the introduction — which is expected some time in the next year or two.

“There are some uncertainties around how to actually regulate generative AI models, distinct from the rest of AI,” Haber said. “We see technological progress advancing much more quickly than the regulatory landscape, which is very challenging. Our role in these conversations is to share developer-first perspectives, because we want to complement policymaking with an understanding of when you put out these regulatory requirements, what do they actually mean for the people in the trenches that are bringing these models out into production?”

Lakera founders: CEO David Haber flanked by CPO Matthias Kraft (left) and CTO Mateo Rojas-Carulla. Image Credits: Lakera

The security blocker

The bottom line is that while ChatGPT and its ilk have taken the world by storm these past nine months like few other technologies have in recent times, enterprises are perhaps more hesitant to adopt generative AI in their applications due to security concerns.

“We speak to some of the coolest startups, to some of the world’s leading enterprises — they either already have these [generative AI apps] in production, or they’re looking at the next three to six months,” Haber said. “And we are already working with them behind the scenes to make sure they can roll this out without any problems. Security is a big blocker for many of these [companies] to bring their generative AI apps to production, which is where we come in.”

Founded out of Zurich in 2021, Lakera already claims major paying customers, which it says it’s not able to name-check due to the security implications of revealing too much about the kinds of protective tools that they’re using. However, the company has confirmed that LLM developer Cohere — a company that recently attained a $2 billion valuation — is a customer, alongside a “leading enterprise cloud platform” and “one of the world’s largest cloud storage services.”

With $10 million in the bank, the company is fairly well-financed to build out its platform now that it’s officially in the public domain.

“We want to be there as people integrate generative AI into their stacks, to make sure these are secure and the risks are mitigated,” Haber said. “So we will evolve the product based on the threat landscape.”

Lakera’s investment was led by Swiss VC Redalpine, with additional capital provided by Fly Ventures, Inovia Capital and several angel investors.

More TechCrunch

TechCrunch Disrupt 2024 will be in San Francisco on October 28–30, and we’re already excited! Disrupt brings innovation for every stage of your startup journey, and we could not bring you this…

Connect with Google Cloud, Aerospace, Qualcomm and more at Disrupt 2024

Featured Article

A comprehensive list of 2024 tech layoffs

The tech layoff wave is still going strong in 2024. Following significant workforce reductions in 2022 and 2023, this year has already seen 60,000 job cuts across 254 companies, according to independent layoffs tracker Layoffs.fyi. Companies like Tesla, Amazon, Google, TikTok, Snap and Microsoft have conducted sizable layoffs in the…

A comprehensive list of 2024 tech layoffs

Intel announced it would layoff more than 15% of its staff, or 15,000 employees, in a memo to employees on Thursday. The massive headcount is part of a large plan…

Intel to lay off 15,000 employees

Following the recent lawsuit filed by the Recording Industry Association of America (RIAA) against music generation startups Udio and Suno, Suno admitted in a court filing on Thursday that it did, in…

AI music startup Suno claims training model on copyrighted music is ‘fair use’

In spite of a drop for the quarter, iPhone remained Apple’s most important category by a wide margin.

iPad sales help bail out Apple amid a continued iPhone slide

Molly Alter wears a lot of hats. She’s a mocumentary filmmaker working on a project about an alternate reality where charades is big business. She’s a caesar salad connoisseur and…

How filming a cappella concerts and dance recitals led Northzone’s newest partner Molly Alter to a career in VC

Microsoft has a long and tangled history with OpenAI, having invested a reported $13 billion in the ChatGPT maker as part of a long-term partnership. As part of the deal,…

Microsoft now lists OpenAI as a competitor in AI and search

The San Jose-based startup raised $60 million in a round that values it lower than the $500 million valuation it garnered in its most recent round, according to multiple sources.

Sequoia-backed Knowde raises Series C at a valuation cut

Self-driving technology company Aurora Innovation is looking to raise hundreds of millions in additional capital as it races toward a driverless commercial launch by the end of 2024.  Aurora is…

Self-driving truck startup Aurora Innovation to sell up to $420M in shares ahead of commercial launch

X (formerly Twitter) can no longer be accessed in the Mac App Store, suggesting that it has been officially delisted.  Searches for both “Twitter” and “X” on Apple’s platform no…

Twitter disappears from Mac App Store

Google Thursday said that it is introducing new Gemini-powered features for Chrome’s desktop version, including Lens for desktop, tab compare for shopping assistance, and natural language integration for search history.…

Google brings Gemini-powered search history and Lens to Chrome desktop

When Xiaoyin Qu was growing up in China, she was obsessed with learning how to build paper airplanes that could do flips in the air. Her parents, though, didn’t have…

Heeyo built an AI chatbot to be a billion kids’ interactive tutor and friend

While the company was awarded a massive, $4.2 billion contract to accelerate Starliner development in 2014, it was structured as a “fixed-price” model.

Boeing bleeds another $125M on Starliner program, bringing total losses to $1.6B

Welcome back to TechCrunch Mobility — your central hub for news and insights on the future of transportation. Sign up here for free — just click TechCrunch Mobility! Summer road…

Anthony Levandowski bets on off-road autonomy, Nuro plots a comeback and Applied Intuition gets more investor love

Google’s new features include Gemini in BigQuery and Looker to help users with data engineering and analysis.

Google Cloud expands its database portfolio with new AI capabilities

Rad Power Bikes, the Seattle-based e-bike startup that has raised more than $300 million from investors, went through another round of layoffs in July, TechCrunch has exclusively learned. This is…

VC darling Rad Power Bikes hit with another round of layoffs

Five years ago, as robotaxis and self-driving truck startups were still raking in millions in venture capital, Anthony Levandowski turned to off-road autonomy. Now, that decision — which brought the…

Why Anthony Levandowski returned to his off-road autonomous vehicle roots with AV startup Pronto

Commercial space station company Vast is building a private microgravity research lab as part of its wider Haven-1 station plans. The module is set to launch no earlier than the…

Vast plans microgravity lab on its Haven-1 private space station

Google Cloud is giving Y Combinator startups access to a dedicated, subsidized cluster of Nvidia graphics processing units and Google tensor processing units to build AI models. It’s part of…

Google Cloud now has a dedicated cluster of Nvidia GPUs for Y Combinator startups

Open source compliance and security platform FOSSA has acquired developer community platform StackShare, the company confirmed to TechCrunch.  StackShare is one of the more popular platforms for developers to discuss,…

Open source startup FOSSA is buying StackShare, a site used by 1.5M developers

Featured Article

Indian startups gut valuations ahead of IPO push

Ola Electric and FirstCry are set to test investor appetite with public listing, both pricing their shares below their previous valuation asks.

Indian startups gut valuations ahead of IPO push

The European Union’s risk-based regulation for applications of artificial intelligence has come into force starting from today.

The EU’s AI Act is now in force

The company also said it has received regulatory clearance to start Phase 2 clinical trials for a new drug in the U.S. later this year.

Healx, an AI-enabled drug discovery platform for rare diseases, raises $47M

The European Commission (EC) has given the go-ahead to HPE’s planned megabucks acquisition of Juniper Networks.

EU greenlights HPE’s $14B Juniper Networks acquisition

Meta, which develops one of the biggest foundational open source large language models, Llama, believes it will need significantly more computing power to train models in the future. Mark Zuckerberg…

Zuckerberg says Meta will need 10x more computing power to train Llama 4 than Llama 3

Axle Energy is a B2B, back-end infrastructure business focused on connecting flexible assets, such as electric vehicles and home batteries, to energy markets that aren’t otherwise available for consumers to…

Axle Energy’s sprint to decarbonize the grid lights up with $9M seed led by Accel

OpenAI CEO Sam Altman says that OpenAI is working with the U.S. AI Safety Institute, a federal government body that aims to assess and address risks in AI platforms, on…

OpenAI pledges to give U.S. AI Safety Institute early access to its next model

WhatsApp’s massive 500 million users in India have supercharged Meta’s AI ambitions. Meta CFO Susan Li said Wednesday that India is the largest market in terms of Meta AI usage,…

Meta says India is the largest market for Meta AI usage

While venture capitalists and the rest of the technorati are off on holiday or attending the Paris Olympics, the U.S. Securities and Exchange Commission and its staff attorneys are keeping…

Founder behind social media app IRL charged with fraud

The serious, long-term negative impact of the bankruptcy of banking-as-a-service (BaaS) fintech Synapse will be significant “on all of fintech, especially consumer-facing services,” one observer has said. In the wake…

Fintech Execs from Synctera, Unit, and Treasury Prime discuss the future of BaaS at TechCrunch Disrupt 2024